mail-lib / mail-extr.el

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
;;; mail-extr.el --- extract full name and address from RFC 822 mail header.

;; Copyright (C) 1991, 1992, 1993, 1994 Free Software Foundation, Inc.

;; Author: Joe Wells <jbw@cs.bu.edu>
;; Maintainer: XEmacs Development Team
;; Version: 1.8
;; Keywords: mail

;; This file is part of XEmacs.

;; XEmacs is free software; you can redistribute it and/or modify it
;; under the terms of the GNU General Public License as published by
;; the Free Software Foundation; either version 2, or (at your option)
;; any later version.

;; XEmacs is distributed in the hope that it will be useful, but
;; WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;; General Public License for more details.

;; You should have received a copy of the GNU General Public License
;; along with XEmacs; see the file COPYING.  If not, write to the 
;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
;; Boston, MA 02111-1307, USA.

;;; Synched up with: Not synched with FSF but close to 19.28.

;;; Commentary:

;; The entry point of this code is
;;
;;    mail-extract-address-components: (address)
;;  
;;    Given an RFC-822 ADDRESS, extract full name and canonical address.
;;    Returns a list of the form (FULL-NAME CANONICAL-ADDRESS).
;;    If no name can be extracted, FULL-NAME will be nil.
;;    ADDRESS may be a string or a buffer.  If it is a buffer, the visible 
;;     (narrowed) portion of the buffer will be interpreted as the address.
;;     (This feature exists so that the clever caller might be able to avoid
;;     consing a string.)
;;    If ADDRESS contains more than one RFC-822 address, only the first is
;;     returned.
;;
;; This code is more correct (and more heuristic) parser than the code in
;; rfc822.el.  And despite its size, it's fairly fast.
;;
;; There are two main benefits:
;;
;; 1. Higher probability of getting the correct full name for a human than
;;    any other package we know of.  (On the other hand, it will cheerfully
;;    mangle non-human names/comments.)
;; 2. Address part is put in a canonical form.
;;
;; The interface is not yet carved in stone; please give us suggestions.
;;
;; We have an extensive test-case collection of funny addresses if you want to
;; work with the code.  Developing this code requires frequent testing to
;; make sure you're not breaking functionality.  The test cases aren't included
;; because they are over 100K.
;;
;; If you find an address that mail-extr fails on, please send it to the 
;; maintainer along with what you think the correct results should be.  We do
;; not consider it a bug if mail-extr mangles a comment that does not
;; correspond to a real human full name, although we would prefer that 
;; mail-extr would return the comment as-is.
;;
;; Features:
;;
;; * Full name handling:
;;
;;   * knows where full names can be found in an address.
;;   * avoids using empty comments and quoted text.
;;   * extracts full names from mailbox names.
;;   * recognizes common formats for comments after a full name.
;;   * puts a period and a space after each initial.
;;   * understands & referring to the mailbox name, capitalized.
;;   * strips name prefixes like "Prof.", etc.
;;   * understands what characters can occur in names (not just letters).
;;   * figures out middle initial from mailbox name.
;;   * removes funny nicknames.
;;   * keeps suffixes such as Jr., Sr., III, etc.
;;   * reorders "Last, First" type names.
;;
;; * Address handling:
;;
;;   * parses rfc822 quoted text, comments, and domain literals.
;;   * parses rfc822 multi-line headers.
;;   * does something reasonable with rfc822 GROUP addresses.
;;   * handles many rfc822 noncompliant and garbage addresses.
;;   * canonicalizes addresses (after stripping comments/phrases outside <>).
;;     * converts ! addresses into .UUCP and %-style addresses.
;;     * converts rfc822 ROUTE addresses to %-style addresses.
;;     * truncates %-style addresses at leftmost fully qualified domain name.
;;     * handles local relative precedence of ! vs. % and @ (untested).
;;
;; It does almost no string creation.  It primarily uses the built-in
;; parsing routines with the appropriate syntax tables.  This should
;; result in greater speed.
;;
;; TODO:
;;
;; * handle all test cases.  (This will take forever.)
;; * software to pick the correct header to use (eg., "Senders-Name:").
;; * multiple addresses in the "From:" header (almost all of the necessary
;;   code is there).
;; * flag to not treat `,' as an address separator.  (This is useful when
;;   there is a "From:" header but no "Sender:" header, because then there
;;   is only allowed to be one address.)
;; * mailbox name does not necessarily contain full name.
;; * fixing capitalization when it's all upper or lowercase.  (Hard!)
;; * some of the domain literal handling is missing.  (But I've never even
;;   seen one of these in a mail address, so maybe no big deal.)
;; * arrange to have syntax tables byte-compiled.
;; * speed hacks.
;; * delete unused variables.
;; * arrange for testing with different relative precedences of ! vs. @
;;   and %.
;; * insert documentation strings!
;; * handle X.400-gatewayed addresses according to RFC 1148.

;;; Change Log: 
;; 
;; Thu Feb 17 17:57:33 1994  Jamie Zawinski (jwz@lucid.com)
;;
;;	* merged with jbw's latest version
;;
;; Wed Feb  9 21:56:27 1994  Jamie Zawinski (jwz@lucid.com)
;;
;;      * high-bit chars in comments weren't treated as word syntax
;;
;; Sat Feb  5 03:13:40 1994  Jamie Zawinski (jwz@lucid.com)
;;
;;      * call replace-match with fixed-case arg
;;
;; Thu Dec 16 21:56:45 1993  Jamie Zawinski (jwz@lucid.com)
;;
;;      * some more cleanup, doc, added provide
;;
;; Tue Mar 23 21:23:18 1993  Joe Wells  (jbw at csd.bu.edu)
;; 
;; 	* Made mail-full-name-prefixes a user-customizable variable.
;;        Allow passing the address as a buffer as well as a string.
;;        Allow [ and ] as name characters (Finnish character set).
;; 
;; Mon Mar 22 21:20:56 1993  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Handle "null" addresses.  Handle = used for spacing in mailbox
;; 	  name.  Fix bug in handling of ROUTE-ADDR-type addresses that are
;; 	  missing their brackets.  Handle uppercase "JR".  Extract full
;; 	  names from X.400 addresses encoded in RFC-822.  Fix bug in
;;        handling of multiple addresses where first has trailing comment.
;;        Handle more kinds of telephone extension lead-ins.
;; 
;; Mon Mar 22 20:16:57 1993  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Handle HZ encoding for embedding GB encoded chinese characters.
;; 
;; Mon Mar 22 00:46:12 1993  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Fixed too broad matching of ham radio call signs.  Fixed bug in
;; 	  handling an unmatched ' in a name string.  Enhanced recognition
;; 	  of when . in the mailbox name terminates the name portion.
;; 	  Narrowed conversion of . to space to only the necessary
;; 	  situation.  Deal with VMS's stupid date stamps.  Handle a unique
;; 	  way of introducing an alternate address.  Fixed spacing bug I
;; 	  introduced in switching last name order.  Fixed bug in handling
;; 	  address with ! and % but no @.  Narrowed the cases in which
;; 	  certain trailing words are discarded.
;; 
;; Sun Mar 21 21:41:06 1993  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Fixed bugs in handling GROUP addresses.  Certain words in the
;; 	  middle of a name no longer terminate it.  Handle LISTSERV list
;;        names.  Ignore comment field containing mailbox name.
;; 
;; Sun Mar 21 14:39:38 1993  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Moved variant-method code back into main function.  Handle
;; 	underscores as spaces in comments.  Handle leading nickname.  Add
;; 	flag to ignore single-word names.  Other changes.
;; 
;; Mon Feb  1 22:23:31 1993  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Added in changes by Rod Whitby and Jamie Zawinski.  This
;;        includes the flag mail-extr-guess-middle-initial and the fix for
;;        handling multiple addresses correctly.
;; 
;; Mon Apr  6 23:59:09 1992  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Cleaned up some more.  Release version 1.0 to world.
;; 
;; Sun Apr  5 19:39:08 1992  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Cleaned up full name extraction extensively.
;; 
;; Sun Feb  2 14:45:24 1992  Joe Wells  (jbw at bigbird.bu.edu)
;; 
;; 	* Total rewrite.  Integrated mail-canonicalize-address into
;; 	mail-extract-address-components.  Now handles GROUP addresses more
;; 	or less correctly.  Better handling of lots of different cases.
;; 
;; Fri Jun 14 19:39:50 1991
;;	* Created.

;;; Code:


;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; User configuration variable definitions.
;;

(defgroup mail-extr nil
  "Extract full name and address from RFC 822 mail header."
  :group 'mail)


(defcustom mail-extr-guess-middle-initial nil
  "*Whether to try to guess middle initial from mail address.
If true, then when we see an address like \"John Smith <jqs@host.com>\"
we will assume that \"John Q. Smith\" is the fellow's name."
  :type 'boolean
  :group 'mail-extr)

(defcustom mail-extr-ignore-single-names t
  "*Whether to ignore a name that is just a single word.
If true, then when we see an address like \"Idiot <dumb@stupid.com>\"
we will act as though we couldn't find a full name in the address."
  :type 'boolean
  :group 'mail-extr)

;; Matches a leading title that is not part of the name (does not
;; contribute to uniquely identifying the person).
(defcustom mail-extr-full-name-prefixes
  "\\(Prof\\|D[Rr]\\|Mrs?\\|Rev\\|Rabbi\\|SysOp\\|LCDR\\)\\.?[ \t\n]"
  "*Matches prefixes to the full name that identify a person's position.
These are stripped from the full name because they do not contribute to
uniquely identifying the person."
  :type 'boolean
  :group 'mail-extr)

(defcustom mail-extr-@-binds-tighter-than-! nil
  "*Whether the local mail transport agent looks at ! before @."
  :type 'boolean
  :group 'mail-extr)

(defcustom mail-extr-mangle-uucp nil
  "*Whether to throw away information in UUCP addresses
by translating things like \"foo!bar!baz@host\" into \"baz@bar.UUCP\"."
  :type 'boolean
  :group 'mail-extr)

(defcustom mail-extr-mailbox-match-case-fold t
  "*Non-nil if mailbox and name matching should ignore case."
  :type 'boolean
  :group 'mail-extr)

;;----------------------------------------------------------------------
;; what orderings are meaningful?????
;;(defvar mail-operator-precedence-list '(?! ?% ?@))
;; Right operand of a % or a @ must be a domain name, period.  No other
;; operators allowed.  Left operand of a @ is an address relative to that
;; site.

;; Left operand of a ! must be a domain name.  Right operand is an
;; arbitrary address.
;;----------------------------------------------------------------------



;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; Constant definitions.
;;

;;           Codes in
;; Names in  ISO 8859-1 Name
;; ISO 10XXX ISO 8859-2 in
;; ISO 6937  ISO 10646  RFC            Swedish
;; etc.      Hex Oct    1345 TeX Split ASCII Description
;; --------- ---------- ---- --- ----- ----- -------------------------------
;; %a        E4  344    a:   \"a ae    {     latin small   a + diaeresis   �
;; %o        F6  366    o:   \"o oe    |     latin small   o + diaeresis   �
;; @a        E5  345    aa   \oa aa    }     latin small   a + ring above  �
;; %u        FC  374    u:   \"u ue    ~     latin small   u + diaeresis   �
;; /e        E9  351    e'   \'e       `     latin small   e + acute       �
;; %A        C4  304    A:   \"A AE    [     latin capital a + diaeresis   �
;; %O        D6  326    O:   \"O OE    \     latin capital o + diaeresis   �
;; @A        C5  305    AA   \oA AA    ]     latin capital a + ring above  �
;; %U        DC  334    U:   \"U UE    ^     latin capital u + diaeresis   �
;; /E        C9  311    E'   \'E       @     latin capital e + acute       �

;; NOTE: @a and @A are not in ISO 8859-2 (the codes mentioned above invoke
;; /l and /L).  Some of this data was retrieved from
;; listserv@jhuvm.hcf.jhu.edu.

;; Any character that can occur in a name, not counting characters that
;; separate parts of a multipart name (hyphen and period).
;; Yes, there are weird people with digits in their names.
;; You will also notice the consideration for the
;; Swedish/Finnish/Norwegian character set.
;; #### (go to \376 instead of \377 to work around bug in search.c...)
(defconst mail-extr-all-letters-but-separators
  (purecopy "][A-Za-z{|}'~0-9`\200-\376"))

;; Any character that can occur in a name in an RFC822 address including
;; the separator (hyphen and possibly period) for multipart names.
;; #### should . be in here?
(defconst mail-extr-all-letters
  (purecopy (concat mail-extr-all-letters-but-separators "---")))

;; Any character that can start a name.
;; Keep this set as minimal as possible.
(defconst mail-extr-first-letters (purecopy "A-Za-z"))

;; Any character that can end a name.
;; Keep this set as minimal as possible.
(defconst mail-extr-last-letters (purecopy "[A-Za-z`'."))

(defconst mail-extr-leading-garbage
  (purecopy (format "[^%s]+" mail-extr-first-letters)))

;; (defconst mail-extr-non-name-chars 
;;   (purecopy (concat "^" mail-extr-all-letters ".")))
;; (defconst mail-extr-non-begin-name-chars
;;   (purecopy (concat "^" mail-extr-first-letters)))
;; (defconst mail-extr-non-end-name-chars
;;   (purecopy (concat "^" mail-extr-last-letters)))

;; Matches an initial not followed by both a period and a space. 
;; (defconst mail-extr-bad-initials-pattern
;;   (purecopy 
;;    (format "\\(\\([^%s]\\|\\`\\)[%s]\\)\\(\\.\\([^ ]\\)\\| \\|\\([^%s .]\\)\\|\\'\\)"
;;            mail-extr-all-letters mail-extr-first-letters mail-extr-all-letters)))

;; Matches periods used instead of spaces.  Must not match the period
;; following an initial.
(defconst mail-extr-bad-dot-pattern
  (purecopy
   (format "\\([%s][%s]\\)\\.+\\([%s]\\)"
	   mail-extr-all-letters
	   mail-extr-last-letters
	   mail-extr-first-letters)))

;; Matches an embedded or leading nickname that should be removed.
;; (defconst mail-extr-nickname-pattern
;;   (purecopy
;;    (format "\\([ .]\\|\\`\\)[\"'`\[\(]\\([ .%s]+\\)[\]\"'\)] "
;;            mail-extr-all-letters)))

;; Matches the occurrence of a generational name suffix, and the last
;; character of the preceding name.  This is important because we want to
;; keep such suffixes: they help to uniquely identify the person.
;; *** Perhaps this should be a user-customizable variable.  However, the
;; *** regular expression is fairly tricky to alter, so maybe not.
(defconst mail-extr-full-name-suffix-pattern
  (purecopy
   (format
    "\\(,? ?\\([JjSs][Rr]\\.?\\|V?I+V?\\)\\)\\([^%s]\\([^%s]\\|\\'\\)\\|\\'\\)"
    mail-extr-all-letters mail-extr-all-letters)))

(defconst mail-extr-roman-numeral-pattern (purecopy "V?I+V?\\b"))

;; Matches a trailing uppercase (with other characters possible) acronym.
;; Must not match a trailing uppercase last name or trailing initial
(defconst mail-extr-weird-acronym-pattern
  (purecopy "\\([A-Z]+[-_/]\\|[A-Z][A-Z][A-Z]?\\b\\)"))
      
;; Matches a mixed-case or lowercase name (not an initial).
;; #### Match Latin1 lower case letters here too?
;; (defconst mail-extr-mixed-case-name-pattern
;;   (purecopy
;;    (format
;;     "\\b\\([a-z][%s]*[%s]\\|[%s][%s]*[a-z][%s]*[%s]\\|[%s][%s]*[a-z]\\)"
;;     mail-extr-all-letters mail-extr-last-letters
;;     mail-extr-first-letters mail-extr-all-letters mail-extr-all-letters
;;     mail-extr-last-letters mail-extr-first-letters mail-extr-all-letters)))

;; Matches a trailing alternative address.
;; #### Match Latin1 letters here too?
;; #### Match _ before @ here too?  
(defconst mail-extr-alternative-address-pattern
  (purecopy "\\(aka *\\)?[a-zA-Z.]+[!@][a-zA-Z.]"))

;; Matches a variety of trailing comments not including comma-delimited
;; comments.
(defconst mail-extr-trailing-comment-start-pattern
  (purecopy " [-{]\\|--\\|[+@#></\;]"))

;; Matches a name (not an initial).
;; This doesn't force a word boundary at the end because sometimes a
;; comment is separated by a `-' with no preceding space.
(defconst mail-extr-name-pattern
  (purecopy (format "\\b[%s][%s]*[%s]"
		    mail-extr-first-letters
		    mail-extr-all-letters
		    mail-extr-last-letters)))

(defconst mail-extr-initial-pattern
  (purecopy (format "\\b[%s]\\([. ]\\|\\b\\)" mail-extr-first-letters)))

;; Matches a single name before a comma.
;; (defconst mail-extr-last-name-first-pattern
;;   (purecopy (concat "\\`" mail-extr-name-pattern ",")))

;; Matches telephone extensions.
(defconst mail-extr-telephone-extension-pattern
  (purecopy
   "\\(\\([Ee]xt\\|\\|[Tt]ph\\|[Tt]el\\|[Xx]\\).?\\)? *\\+?[0-9][- 0-9]+"))

;; Matches ham radio call signs.
;; Help from: Mat Maessen N2NJZ <maessm@rpi.edu>, Mark Feit
;; <mark@era.com>, Michael Covington <mcovingt@ai.uga.edu>.
;; Examples: DX504 DX515 K5MRU K8DHK KA9WGN KA9WGN KD3FU KD6EUI KD6HBW
;; KE9TV KF0NV N1API N3FU N3GZE N3IGS N4KCC N7IKQ N9HHU W4YHF W6ANK WA2SUH
;; WB7VZI N2NJZ NR3G KJ4KK AB4UM AL7NI KH6OH WN3KBT N4TMI W1A N0NZO
(defconst mail-extr-ham-call-sign-pattern
  (purecopy "\\b\\(DX[0-9]+\\|[AKNW][A-Z]?[0-9][A-Z][A-Z]?[A-Z]?\\)"))

;; Possible trailing suffixes: "\\(/\\(KT\\|A[AEG]\\|[R0-9]\\)\\)?"
;; /KT == Temporary Technician (has CSC but not "real" license)
;; /AA == Temporary Advanced
;; /AE == Temporary Extra
;; /AG == Temporary General
;; /R  == repeater
;; /#  == stations operating out of home district
;; I don't include these in the regexp above because I can't imagine
;; anyone putting them with their name in an e-mail address.

;; Matches normal single-part name
(defconst mail-extr-normal-name-pattern
  (purecopy (format "\\b[%s][%s]+[%s]"
		    mail-extr-first-letters
		    mail-extr-all-letters-but-separators
		    mail-extr-last-letters)))

;; Matches a single word name.
;; (defconst mail-extr-one-name-pattern
;;   (purecopy (concat "\\`" mail-extr-normal-name-pattern "\\'")))
  
;; Matches normal two names with missing middle initial
;; The first name is not allowed to have a hyphen because this can cause
;; false matches where the "middle initial" is actually the first letter
;; of the second part of the first name.
(defconst mail-extr-two-name-pattern
  (purecopy
   (concat "\\`\\(" mail-extr-normal-name-pattern
	   "\\|" mail-extr-initial-pattern
	   "\\) +\\(" mail-extr-name-pattern "\\)\\(,\\|\\'\\)")))

(defconst mail-extr-listserv-list-name-pattern
  (purecopy "Multiple recipients of list \\([-A-Z]+\\)"))

(defconst mail-extr-stupid-vms-date-stamp-pattern
  (purecopy
   "[0-9][0-9]-[JFMASOND][aepuco][nbrylgptvc]-[0-9][0-9][0-9][0-9] [0-9]+ *"))

;;; HZ -- GB (PRC Chinese character encoding) in ASCII embedding protocol
;;
;; In ASCII mode, a byte is interpreted as an ASCII character, unless a '~' is
;; encountered. The character '~' is an escape character. By convention, it
;; must be immediately followed ONLY by '~', '{' or '\n' (<LF>), with the
;; following special meaning.
;; 
;; o The escape sequence '~~' is interpreted as a '~'.
;; o The escape-to-GB sequence '~{' switches the mode from ASCII to GB.
;; o The escape sequence '~\n' is a line-continuation marker to be consumed
;;   with no output produced.
;; 
;; In GB mode, characters are interpreted two bytes at a time as (pure) GB
;; codes until the escape-from-GB code '~}' is read. This code switches the
;; mode from GB back to ASCII.  (Note that the escape-from-GB code '~}'
;; ($7E7D) is outside the defined GB range.)
(defconst mail-extr-hz-embedded-gb-encoded-chinese-pattern
  (purecopy "~{\\([^~].\\|~[^\}]\\)+~}"))

;; The leading optional lowercase letters are for a bastardized version of
;; the encoding, as is the optional nature of the final slash.
(defconst mail-extr-x400-encoded-address-pattern
  (purecopy "[a-z]?[a-z]?\\(/[A-Za-z]+\\(\\.[A-Za-z]+\\)?=[^/]+\\)+/?\\'"))

(defconst mail-extr-x400-encoded-address-field-pattern-format
  (purecopy "/%s=\\([^/]+\\)\\(/\\|\\'\\)"))

(defconst mail-extr-x400-encoded-address-surname-pattern
  ;; S stands for Surname (family name).
  (purecopy
   (format mail-extr-x400-encoded-address-field-pattern-format "[Ss]")))

(defconst mail-extr-x400-encoded-address-given-name-pattern
  ;; G stands for Given name.
  (purecopy
   (format mail-extr-x400-encoded-address-field-pattern-format "[Gg]")))

(defconst mail-extr-x400-encoded-address-full-name-pattern
  ;; PN stands for Personal Name.  When used it represents the combination
  ;; of the G and S fields.
  ;; "The one system I used having this field asked it with the prompt
  ;; `Personal Name'.  But they mapped it into G and S on outgoing real
  ;; X.400 addresses.  As they mapped G and S into PN on incoming..."
  (purecopy
   (format mail-extr-x400-encoded-address-field-pattern-format "[Pp][Nn]")))



;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; Syntax tables used for quick parsing.
;;

(defconst mail-extr-address-syntax-table (make-syntax-table))
(defconst mail-extr-address-comment-syntax-table (make-syntax-table))
(defconst mail-extr-address-domain-literal-syntax-table (make-syntax-table))
(defconst mail-extr-address-text-comment-syntax-table (make-syntax-table))
(defconst mail-extr-address-text-syntax-table (make-syntax-table))
(mapcar
 (function
  (lambda (pair)
    (let ((syntax-table (symbol-value (car pair))))
      (mapcar
       (function
	(lambda (item)
	  (if (eq 2 (length item))
	      ;; modifying syntax of a single character
	      (modify-syntax-entry (car item) (car (cdr item)) syntax-table)
	    ;; modifying syntax of a range of characters
	    (let ((char (nth 0 item))
		  (bound (nth 1 item))
		  (syntax (nth 2 item)))
	      (while (<= char bound)
		(modify-syntax-entry char syntax syntax-table)
		(setq char (1+ char)))))))
       (cdr pair)))))
 '((mail-extr-address-syntax-table
    (?\000 ?\037 "w")			;control characters
    (?\040	 " ")			;SPC
    (?! ?~	 "w")			;printable characters
    (?\177	 "w")			;DEL
    (?\200 ?\377 "w")			;high-bit-on characters
    (?\240	 " ")			;nobreakspace
    (?\t " ")
    (?\r " ")
    (?\n " ")
    (?\( ".")
    (?\) ".")
    (?<  ".")
    (?>  ".")
    (?@  ".")
    (?,  ".")
    (?\; ".")
    (?:  ".")
    (?\\ "\\")
    (?\" "\"")
    (?.  ".")
    (?\[ ".")
    (?\] ".")
    ;; % and ! aren't RFC822 characters, but it is convenient to pretend
    (?%  ".")
    (?!  ".") ;; this needs to be word-constituent when not in .UUCP mode
    )
   (mail-extr-address-comment-syntax-table
    (?\000 ?\377 "w")
    (?\040 " ")
    (?\240 " ")
    (?\t " ")
    (?\r " ")
    (?\n " ")
    (?\( "\(\)")
    (?\) "\)\(")
    (?\\ "\\"))
   (mail-extr-address-domain-literal-syntax-table
    (?\000 ?\377 "w")
    (?\040 " ")
    (?\240 " ")
    (?\t " ")
    (?\r " ")
    (?\n " ")
    (?\[ "\(\]")			;??????
    (?\] "\)\[")			;??????
    (?\\ "\\"))
   (mail-extr-address-text-comment-syntax-table
    (?\000 ?\377 "w")
    (?\040 " ")
    (?\240 " ")
    (?\t " ")
    (?\r " ")
    (?\n " ")
    (?\( "\(\)")
    (?\) "\)\(")
    (?\[ "\(\]")
    (?\] "\)\[")
    (?\{ "\(\}")
    (?\} "\)\{")
    (?\\ "\\")
    (?\" "\"")
    ;; (?\' "\)\`")
    ;; (?\` "\(\'")
    )
   (mail-extr-address-text-syntax-table
    (?\000 ?\177 ".")
    (?\200 ?\377 "w")
    (?\040 " ")
    (?\t " ")
    (?\r " ")
    (?\n " ")
    (?A ?Z "w")
    (?a ?z "w")
    (?-    "w")
    (?\}   "w")
    (?\{   "w")
    (?|    "w")
    (?\'   "w")
    (?~    "w")
    (?0 ?9 "w"))
   ))


;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; Utility functions and macros.
;;

(defmacro mail-extr-delete-char (n)
  ;; in v19, delete-char is compiled as a function call, but delete-region
  ;; is byte-coded, so it's much much faster.
  (list 'delete-region '(point) (list '+ '(point) n)))

(defmacro mail-extr-skip-whitespace-forward ()
  ;; v19 fn skip-syntax-forward is more tasteful, but not byte-coded.
  '(skip-chars-forward " \t\n\r\240"))

(defmacro mail-extr-skip-whitespace-backward ()
  ;; v19 fn skip-syntax-backward is more tasteful, but not byte-coded.
  '(skip-chars-backward " \t\n\r\240"))


(defmacro mail-extr-undo-backslash-quoting (beg end)
  (`(save-excursion
      (save-restriction
	(narrow-to-region (, beg) (, end))
	(goto-char (point-min))
	;; undo \ quoting
	(while (search-forward "\\" nil t)
	  (mail-extr-delete-char -1)
	  (or (eobp)
	      (forward-char 1))
	  )))))

(defmacro mail-extr-nuke-char-at (pos)
  (` (save-excursion
       (goto-char (, pos))
       (mail-extr-delete-char 1)
       (insert ?\ ))))

(put 'mail-extr-nuke-outside-range
     'edebug-form-spec '(symbolp &optional form form atom))

(defmacro mail-extr-nuke-outside-range (list-symbol
					beg-symbol end-symbol
					&optional no-replace)
  ;; LIST-SYMBOL names a variable holding a list of buffer positions
  ;; BEG-SYMBOL and END-SYMBOL name variables delimiting a range
  ;; Each element of LIST-SYMBOL which lies outside of the range is
  ;;  deleted from the list.
  ;; Unless NO-REPLACE is true, at each of the positions in LIST-SYMBOL
  ;;  which lie outside of the range, one character at that position is
  ;;  replaced with a SPC.
  (or (memq no-replace '(t nil))
      (error "no-replace must be t or nil, evalable at macroexpand-time."))
  (` (let ((temp (, list-symbol))
	   ch)
       (while temp
	 (setq ch (car temp))
	 (cond ((or (> ch (, end-symbol))
		    (< ch (, beg-symbol)))
		(,@ (if no-replace
			nil
		      (` ((mail-extr-nuke-char-at ch)))))
		(setcar temp nil)))
	 (setq temp (cdr temp)))
       (setq (, list-symbol) (delq nil (, list-symbol))))))

(defun mail-extr-demarkerize (marker)
  ;; if arg is a marker, destroys the marker, then returns the old value.
  ;; otherwise returns the arg.
  (if (markerp marker)
      (let ((temp (marker-position marker)))
	(set-marker marker nil)
	temp)
    marker))

(defun mail-extr-markerize (pos)
  ;; coerces pos to a marker if non-nil.
  (if (or (markerp pos) (null pos))
      pos
    (copy-marker pos)))

(defmacro mail-extr-last (list)
  ;; Returns last element of LIST.
  ;; Could be a subst.
  (` (let ((list (, list)))
       (while (not (null (cdr list)))
	 (setq list (cdr list)))
       (car list))))
  
(defmacro mail-extr-safe-move-sexp (arg)
  ;; Safely skip over one balanced sexp, if there is one.  Return t if success.
  (` (condition-case error
	 (progn
	   (goto-char (scan-sexps (point) (, arg)))
	   t)
       (error
	;; #### kludge kludge kludge kludge kludge kludge kludge !!!
	(if (string-equal (nth 1 error) "Unbalanced parentheses")
	    nil
	  (while t
	    (signal (car error) (cdr error))))))))


;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; The main function to grind addresses
;;

(defvar disable-initial-guessing-flag)	; dynamic assignment
(defvar cbeg)				; dynamic assignment
(defvar cend)				; dynamic assignment

;;;###autoload
(defun mail-extract-address-components (address)
  "Given an RFC-822 ADDRESS, extract full name and canonical address.
Returns a list of the form (FULL-NAME CANONICAL-ADDRESS).
If no name can be extracted, FULL-NAME will be nil.
ADDRESS may be a string or a buffer.  If it is a buffer, the visible 
 (narrowed) portion of the buffer will be interpreted as the address.
 (This feature exists so that the clever caller might be able to avoid
 consing a string.)
If ADDRESS contains more than one RFC-822 address, only the first is
 returned.  Some day this function may be extended to extract multiple
 addresses, or perhaps return the position at which parsing stopped."
  (let ((canonicalization-buffer (get-buffer-create " *canonical address*"))
	(extraction-buffer (get-buffer-create " *extract address components*"))
	char
;;	multiple-addresses
	<-pos >-pos @-pos colon-pos comma-pos !-pos %-pos \;-pos
	group-colon-pos group-\;-pos route-addr-colon-pos
	record-pos-symbol
	first-real-pos last-real-pos
	phrase-beg phrase-end
	cbeg cend			; dynamically set from -voodoo
	quote-beg quote-end
	atom-beg atom-end
	mbox-beg mbox-end
	\.-ends-name
	temp
;;	name-suffix
	fi mi li			; first, middle, last initial
	saved-%-pos saved-!-pos saved-@-pos
	domain-pos \.-pos insert-point
;;	mailbox-name-processed-flag
	disable-initial-guessing-flag	; dynamically set from -voodoo
	)
    
    (save-excursion
      (set-buffer extraction-buffer)
      (fundamental-mode)
      (kill-all-local-variables)
      (buffer-disable-undo extraction-buffer)
      (set-syntax-table mail-extr-address-syntax-table)
      (widen)
      (erase-buffer)
      (setq case-fold-search nil)
      
      ;; Insert extra space at beginning to allow later replacement with <
      ;; without having to move markers.
      (insert ?\ )

      ;; Insert the address itself.
      (cond ((stringp address)
	     (insert address))
	    ((bufferp address)
	     (insert-buffer-substring address))
	    (t
	     (error "Illegal address: %s" address)))
      
      ;; stolen from rfc822.el
      ;; Unfold multiple lines.
      (goto-char (point-min))
      (while (re-search-forward "\\([^\\]\\(\\\\\\\\\\)*\\)\n[ \t]" nil t)
	(replace-match "\\1 " t))
      
      ;; first pass grabs useful information about address
      (goto-char (point-min))
      (while (progn
	       (mail-extr-skip-whitespace-forward)
	       (not (eobp)))
	(setq char (char-after (point)))
	(or first-real-pos
	    (if (not (eq char ?\())
		(setq first-real-pos (point))))
	(cond
	 ;; comment
	 ((eq char ?\()
	  (set-syntax-table mail-extr-address-comment-syntax-table)
	  ;; only record the first non-empty comment's position
	  (if (and (not cbeg)
		   (save-excursion
		     (forward-char 1)
		     (mail-extr-skip-whitespace-forward)
		     (not (eq ?\) (char-after (point))))))
	      (setq cbeg (point)))
	  ;; TODO: don't record if unbalanced
	  (or (mail-extr-safe-move-sexp 1)
	      (forward-char 1))
	  (set-syntax-table mail-extr-address-syntax-table)
	  (if (and cbeg
		   (not cend))
	      (setq cend (point))))
	 ;; quoted text
	 ((eq char ?\")
	  ;; only record the first non-empty quote's position
	  (if (and (not quote-beg)
		   (save-excursion
		     (forward-char 1)
		     (mail-extr-skip-whitespace-forward)
		     (not (eq ?\" (char-after (point))))))
	      (setq quote-beg (point)))
	  ;; TODO: don't record if unbalanced
	  (or (mail-extr-safe-move-sexp 1)
	      (forward-char 1))
	  (if (and quote-beg
		   (not quote-end))
	      (setq quote-end (point))))
	 ;; domain literals
	 ((eq char ?\[)
	  (set-syntax-table mail-extr-address-domain-literal-syntax-table)
	  (or (mail-extr-safe-move-sexp 1)
	      (forward-char 1))
	  (set-syntax-table mail-extr-address-syntax-table))
	 ;; commas delimit addresses when outside < > pairs.
	 ((and (eq char ?,)
	       (or (and (null <-pos)
			;; Handle ROUTE-ADDR address that is missing its <.
			(not (eq ?@ (char-after (1+ (point))))))
		   (and >-pos
			;; handle weird munged addresses
			;; BUG FIX: This test was reversed.  Thanks to the
			;; brilliant Rod Whitby <rwhitby@research.canon.oz.au>
			;; for discovering this!
			(< (mail-extr-last <-pos) (car >-pos)))))
;; It'd be great if some day this worked, but for now, punt.
;;	  (setq multiple-addresses t)
;;	  ;; *** Why do I want this:
;;	  (mail-extr-delete-char 1)
;;	  (narrow-to-region (point-min) (point))
	  (delete-region (point) (point-max))
	  (setq char ?\() ; HAVE I NO SHAME??
	  )
	 ;; record the position of various interesting chars, determine
	 ;; legality later.
	 ((setq record-pos-symbol
		(cdr (assq char
			   '((?< . <-pos) (?> . >-pos) (?@ . @-pos)
			     (?: . colon-pos) (?, . comma-pos) (?! . !-pos)
			     (?% . %-pos) (?\; . \;-pos)))))
	  (set record-pos-symbol
	       (cons (point) (symbol-value record-pos-symbol)))
	  (forward-char 1))
	 ((eq char ?.)
	  (forward-char 1))
	 ((memq char '(
		       ;; comment terminator illegal
		       ?\)
		       ;; domain literal terminator illegal
		       ?\]
		       ;; \ allowed only within quoted strings,
		       ;; domain literals, and comments
		       ?\\
		       ))
	  (mail-extr-nuke-char-at (point))
	  (forward-char 1))
	 (t
	  (forward-word 1)))
	(or (eq char ?\()
	    ;; At the end of first address of a multiple address header.
	    (and (eq char ?,)
		 (eobp))
	    (setq last-real-pos (point))))
      
      ;; Use only the leftmost <, if any.  Replace all others with spaces.
      (while (cdr <-pos)
	(mail-extr-nuke-char-at (car <-pos))
	(setq <-pos (cdr <-pos)))
      
      ;; Use only the rightmost >, if any.  Replace all others with spaces.
      (while (cdr >-pos)
	(mail-extr-nuke-char-at (nth 1 >-pos))
	(setcdr >-pos (nthcdr 2 >-pos)))
      
      ;; If multiple @s and a :, but no < and >, insert around buffer.
      ;; Example: @foo.bar.dom,@xxx.yyy.zzz:mailbox@aaa.bbb.ccc
      ;; This commonly happens on the UUCP "From " line.  Ugh.
      (cond ((and (> (length @-pos) 1)
		  (eq 1 (length colon-pos))	;TODO: check if between last two @s
		  (not \;-pos)
		  (not <-pos))
	     (goto-char (point-min))
	     (mail-extr-delete-char 1)
	     (setq <-pos (list (point)))
	     (insert ?<)))
      
      ;; If < but no >, insert > in rightmost possible position
      (cond ((and <-pos
		  (null >-pos))
	     (goto-char (point-max))
	     (setq >-pos (list (point)))
	     (insert ?>)))
      
      ;; If > but no <, replace > with space.
      (cond ((and >-pos
		  (null <-pos))
	     (mail-extr-nuke-char-at (car >-pos))
	     (setq >-pos nil)))

      ;; Turn >-pos and <-pos into non-lists
      (setq >-pos (car >-pos)
	    <-pos (car <-pos))
      
      ;; Trim other punctuation lists of items outside < > pair to handle
      ;; stupid MTAs.
      (cond (<-pos			; don't need to check >-pos also
	     ;; handle bozo software that violates RFC 822 by sticking
	     ;; punctuation marks outside of a < > pair
	     (mail-extr-nuke-outside-range @-pos <-pos >-pos t)
	     ;; RFC 822 says nothing about these two outside < >, but
	     ;; remove those positions from the lists to make things
	     ;; easier.
	     (mail-extr-nuke-outside-range !-pos <-pos >-pos t)
	     (mail-extr-nuke-outside-range %-pos <-pos >-pos t)))
      
      ;; Check for : that indicates GROUP list and for : part of
      ;; ROUTE-ADDR spec.
      ;; Can't possibly be more than two :.  Nuke any extra.
      (while colon-pos
	(setq temp (car colon-pos)
	      colon-pos (cdr colon-pos))
	(cond ((and <-pos >-pos
		    (> temp <-pos)
		    (< temp >-pos))
	       (if (or route-addr-colon-pos
		       (< (length @-pos) 2)
		       (> temp (car @-pos))
		       (< temp (nth 1 @-pos)))
		   (mail-extr-nuke-char-at temp)
		 (setq route-addr-colon-pos temp)))
	      ((or (not <-pos)
		   (and <-pos
			(< temp <-pos)))
	       (setq group-colon-pos temp))))
      
      ;; Nuke any ; that is in or to the left of a < > pair or to the left
      ;; of a GROUP starting :.  Also, there may only be one ;.
      (while \;-pos
	(setq temp (car \;-pos)
	      \;-pos (cdr \;-pos))
	(cond ((and <-pos >-pos
		    (> temp <-pos)
		    (< temp >-pos))
	       (mail-extr-nuke-char-at temp))
	      ((and (or (not group-colon-pos)
			(> temp group-colon-pos))
		    (not group-\;-pos))
	       (setq group-\;-pos temp))))
      
      ;; Nuke unmatched GROUP syntax characters.
      (cond ((and group-colon-pos (not group-\;-pos))
	     ;; *** Do I really need to erase it?
	     (mail-extr-nuke-char-at group-colon-pos)
	     (setq group-colon-pos nil)))
      (cond ((and group-\;-pos (not group-colon-pos))
	     ;; *** Do I really need to erase it?
	     (mail-extr-nuke-char-at group-\;-pos)
	     (setq group-\;-pos nil)))
      
      ;; Handle junk like ";@host.company.dom" that sendmail adds.
      ;; **** should I remember comment positions?
      (cond
       (group-\;-pos
	;; this is fine for now
	(mail-extr-nuke-outside-range !-pos group-colon-pos group-\;-pos t)
	(mail-extr-nuke-outside-range @-pos group-colon-pos group-\;-pos t)
	(mail-extr-nuke-outside-range %-pos group-colon-pos group-\;-pos t)
	(mail-extr-nuke-outside-range comma-pos group-colon-pos group-\;-pos t)
	(and last-real-pos
	     (> last-real-pos (1+ group-\;-pos))
	     (setq last-real-pos (1+ group-\;-pos)))
	;; *** This may be wrong:
        (and cend
             (> cend group-\;-pos)
             (setq cend nil
                   cbeg nil))
	(and quote-end
	     (> quote-end group-\;-pos)
	     (setq quote-end nil
		   quote-beg nil))
	;; This was both wrong and unnecessary:
	;;(narrow-to-region (point-min) group-\;-pos)

	;; *** The entire handling of GROUP addresses seems rather lame.
	;; *** It deserves a complete rethink, except that these addresses
	;; *** are hardly ever seen.
	))
      
      ;; Any commas must be between < and : of ROUTE-ADDR.  Nuke any
      ;; others.
      ;; Hell, go ahead an nuke all of the commas.
      ;; **** This will cause problems when we start handling commas in
      ;; the PHRASE part .... no it won't ... yes it will ... ?????
      (mail-extr-nuke-outside-range comma-pos 1 1)
      
      ;; can only have multiple @s inside < >.  The fact that some MTAs
      ;; put de-bracketed ROUTE-ADDRs in the UUCP-style "From " line is
      ;; handled above.
      
      ;; Locate PHRASE part of ROUTE-ADDR.
      (cond (<-pos
	     (goto-char <-pos)
	     (mail-extr-skip-whitespace-backward)
	     (setq phrase-end (point))
	     (goto-char (or ;;group-colon-pos
			    (point-min)))
	     (mail-extr-skip-whitespace-forward)
	     (if (< (point) phrase-end)
		 (setq phrase-beg (point))
	       (setq phrase-end nil))))
      
      ;; handle ROUTE-ADDRS with real ROUTEs.
      ;; If there are multiple @s, then we assume ROUTE-ADDR syntax, and
      ;; any % or ! must be semantically meaningless.
      ;; TODO: do this processing into canonicalization buffer
      (cond (route-addr-colon-pos
	     (setq !-pos nil
		   %-pos nil
		   >-pos (copy-marker >-pos)
		   route-addr-colon-pos (copy-marker route-addr-colon-pos))
	     (goto-char >-pos)
	     (insert-before-markers ?X)
	     (goto-char (car @-pos))
	     (while (setq @-pos (cdr @-pos))
	       (mail-extr-delete-char 1)
	       (setq %-pos (cons (point-marker) %-pos))
	       (insert "%")
	       (goto-char (1- >-pos))
	       (save-excursion
		 (insert-buffer-substring extraction-buffer
					  (car @-pos) route-addr-colon-pos)
		 (delete-region (car @-pos) route-addr-colon-pos))
	       (or (cdr @-pos)
		   (setq saved-@-pos (list (point)))))
	     (setq @-pos saved-@-pos)
	     (goto-char >-pos)
	     (mail-extr-delete-char -1)
	     (mail-extr-nuke-char-at route-addr-colon-pos)
	     (mail-extr-demarkerize route-addr-colon-pos)
	     (setq route-addr-colon-pos nil
		   >-pos (mail-extr-demarkerize >-pos)
		   %-pos (mapcar 'mail-extr-demarkerize %-pos))))
      
      ;; de-listify @-pos
      (setq @-pos (car @-pos))
      
      ;; TODO: remove comments in the middle of an address
      
      (set-buffer canonicalization-buffer)
      (fundamental-mode)
      (kill-all-local-variables)
      (buffer-disable-undo canonicalization-buffer)
      (set-syntax-table mail-extr-address-syntax-table)
      (setq case-fold-search nil)
      
      (widen)
      (erase-buffer)
      (insert-buffer-substring extraction-buffer)
      
      (if <-pos
	  (narrow-to-region (progn
			      (goto-char (1+ <-pos))
			      (mail-extr-skip-whitespace-forward)
			      (point))
			    >-pos)
	(if (and first-real-pos last-real-pos)
	    (narrow-to-region first-real-pos last-real-pos)
	  ;; ****** Oh no!  What if the address is completely empty!
	  ;; *** Is this correct?
	  (narrow-to-region (point-max) (point-max))
	  ))
      
      (and @-pos %-pos
	   (mail-extr-nuke-outside-range %-pos (point-min) @-pos))
      (and %-pos !-pos
	   (mail-extr-nuke-outside-range !-pos (point-min) (car %-pos)))
      (and @-pos !-pos (not %-pos)
	   (mail-extr-nuke-outside-range !-pos (point-min) @-pos))
      
      ;; Error condition:?? (and %-pos (not @-pos))
      
      ;; WARNING: THIS CODE IS DUPLICATED BELOW.
      (cond ((and %-pos
		  (not @-pos))
	     (goto-char (car %-pos))
	     (mail-extr-delete-char 1)
	     (setq @-pos (point))
	     (insert "@")
	     (setq %-pos (cdr %-pos))))

      (if mail-extr-mangle-uucp
      (cond (!-pos
	     ;; **** I don't understand this save-restriction and the
	     ;; narrow-to-region inside it.  Why did I do that?
	     (save-restriction
	       (cond ((and @-pos
			   mail-extr-@-binds-tighter-than-!)
		      (goto-char @-pos)
		      (setq %-pos (cons (point) %-pos)
			    @-pos nil)
		      (mail-extr-delete-char 1)
		      (insert "%")
		      (setq insert-point (point-max)))
		     (mail-extr-@-binds-tighter-than-!
		      (setq insert-point (point-max)))
		     (%-pos
		      (setq insert-point (mail-extr-last %-pos)
			    saved-%-pos (mapcar 'mail-extr-markerize %-pos)
			    %-pos nil
			    @-pos (mail-extr-markerize @-pos)))
		     (@-pos
		      (setq insert-point @-pos)
		      (setq @-pos (mail-extr-markerize @-pos)))
		     (t
		      (setq insert-point (point-max))))
	       (narrow-to-region (point-min) insert-point)
	       (setq saved-!-pos (car !-pos))
	       (while !-pos
		 (goto-char (point-max))
		 (cond ((and (not @-pos)
			     (not (cdr !-pos)))
			(setq @-pos (point))
			(insert-before-markers "@ "))
		       (t
			(setq %-pos (cons (point) %-pos))
			(insert-before-markers "% ")))
		 (backward-char 1)
		 (insert-buffer-substring 
		  (current-buffer)
		  (if (nth 1 !-pos)
		      (1+ (nth 1 !-pos))
		    (point-min))
		  (car !-pos))
		 (mail-extr-delete-char 1)
		 (or (save-excursion
		       (mail-extr-safe-move-sexp -1)
		       (mail-extr-skip-whitespace-backward)
		       (eq ?. (char-before)))
		     (insert-before-markers
		      (if (save-excursion
			    (mail-extr-skip-whitespace-backward)
			    (eq ?. (char-before)))
			  ""
			".")
		      "uucp"))
		 (setq !-pos (cdr !-pos))))
	     (and saved-%-pos
		  (setq %-pos (append (mapcar 'mail-extr-demarkerize
					      saved-%-pos)
				      %-pos)))
	     (setq @-pos (mail-extr-demarkerize @-pos))
	     (narrow-to-region (1+ saved-!-pos) (point-max)))))

      ;; WARNING: THIS CODE IS DUPLICATED ABOVE.
      (cond ((and %-pos
		  (not @-pos))
	     (goto-char (car %-pos))
	     (mail-extr-delete-char 1)
	     (setq @-pos (point))
	     (insert "@")
	     (setq %-pos (cdr %-pos))))

      (setq %-pos (nreverse %-pos))
      ;; RFC 1034 doesn't approve of this, oh well:
      ;; Neither do we, sb/lmi
      ;; (downcase-region (or (car %-pos) @-pos (point-max)) (point-max))
      (cond (%-pos			; implies @-pos valid
	     (setq temp %-pos)
	     (catch 'truncated
	       (while temp
		 (goto-char (or (nth 1 temp)
				@-pos))
		 (mail-extr-skip-whitespace-backward)
		 (save-excursion
		   (mail-extr-safe-move-sexp -1)
		   (setq domain-pos (point))
		   (mail-extr-skip-whitespace-backward)
		   (setq \.-pos (eq ?. (char-before))))
		 (cond ((and \.-pos
			     ;; #### string consing
			     (let ((s (intern-soft
				       (buffer-substring domain-pos (point))
				       all-top-level-domains)))
			       (and s (get s 'domain-name))))
			(narrow-to-region (point-min) (point))
			(goto-char (car temp))
			(mail-extr-delete-char 1)
			(setq @-pos (point))
			(setcdr temp nil)
			(setq %-pos (delq @-pos %-pos))
			(insert "@")
			(throw 'truncated t)))
		 (setq temp (cdr temp))))))
      (setq mbox-beg (point-min)
	    mbox-end (if %-pos (car %-pos)
		       (or @-pos
			   (point-max))))
      
      ;; Done canonicalizing address.
      
      (set-buffer extraction-buffer)
      
      ;; Decide what part of the address to search to find the full name.
      (cond (
	     ;; Example: "First M. Last" <fml@foo.bar.dom>
	     (and phrase-beg
		  (eq quote-beg phrase-beg)
		  (<= quote-end phrase-end))
	     (narrow-to-region (1+ quote-beg) (1- quote-end))
	     (mail-extr-undo-backslash-quoting (point-min) (point-max)))

	    ;; Example: First Last <fml@foo.bar.dom>
	    (phrase-beg
	     (narrow-to-region phrase-beg phrase-end))

	    ;; Example: fml@foo.bar.dom (First M. Last)
	    (cbeg
	     (narrow-to-region (1+ cbeg) (1- cend))
	     (mail-extr-undo-backslash-quoting (point-min) (point-max))
	     
	     ;; Deal with spacing problems
	     (goto-char (point-min))
;	     (cond ((not (search-forward " " nil t))
;		    (goto-char (point-min))
;		    (cond ((search-forward "_" nil t)
;			   ;; Handle the *idiotic* use of underlines as spaces.
;			   ;; Example: fml@foo.bar.dom (First_M._Last)
;			   (goto-char (point-min))
;			   (while (search-forward "_" nil t)
;			     (replace-match " " t)))
;			  ((search-forward "." nil t)
;			   ;; Fix . used as space
;			   ;; Example: danj1@cb.att.com (daniel.jacobson)
;			   (goto-char (point-min))
;			   (while (re-search-forward mail-extr-bad-dot-pattern nil t)
;			     (replace-match "\\1 \\2" t))))))
	     )
	    
	    ;; Otherwise we try to get the name from the mailbox portion
	    ;; of the address.
	    ;; Example: First_M_Last@foo.bar.dom
	    (t
	     ;; *** Work in canon buffer instead?  No, can't.  Hmm.
	     (goto-char (point-max))
	     (narrow-to-region (point) (point))
	     (insert-buffer-substring canonicalization-buffer
				      mbox-beg mbox-end)
	     (goto-char (point-min))
	     
	     ;; Example: First_Last.XXX@foo.bar.dom
	     (setq \.-ends-name (re-search-forward "[_0-9]" nil t))
	     
	     (goto-char (point-min))

	     (if (not mail-extr-mangle-uucp)
		 (modify-syntax-entry ?! "w" (syntax-table)))

	     (while (progn
		      (mail-extr-skip-whitespace-forward)
		      (not (eobp)))
	       (setq char (char-after (point)))
	       (cond
		((eq char ?\")
		 (setq quote-beg (point))
		 (or (mail-extr-safe-move-sexp 1)
		     ;; TODO: handle this error condition!!!!!
		     (forward-char 1))
		 ;; take into account deletions
		 (setq quote-end (- (point) 2))
		 (save-excursion
		   (backward-char 1)
		   (mail-extr-delete-char 1)
		   (goto-char quote-beg)
		   (mail-extr-delete-char 1))
		 (mail-extr-undo-backslash-quoting quote-beg quote-end)
		 (or (eq ?\  (char-after (point)))
		     (insert " "))
;;		 (setq mailbox-name-processed-flag t)
		 (setq \.-ends-name t))
		((eq char ?.)
		 (if (memq (char-after (1+ (point))) '(?_ ?=))
		     (progn
		       (forward-char 1)
		       (mail-extr-delete-char 1)
		       (insert ?\ ))
		   (if \.-ends-name
		       (narrow-to-region (point-min) (point))
		     (mail-extr-delete-char 1)
		     (insert " ")))
;;		 (setq mailbox-name-processed-flag t)
		 )
		((memq (char-syntax char) '(?. ?\\))
		 (mail-extr-delete-char 1)
		 (insert " ")
;;		 (setq mailbox-name-processed-flag t)
		 )
		(t
		 (setq atom-beg (point))
		 (forward-word 1)
		 (setq atom-end (point))
		 (goto-char atom-beg)
		 (save-restriction
		   (narrow-to-region atom-beg atom-end)
		   (cond
		    
		    ;; Handle X.400 addresses encoded in RFC-822.
		    ;; *** Shit!  This has to handle the case where it is
		    ;; *** embedded in a quote too!
		    ;; *** Shit!  The input is being broken up into atoms
		    ;; *** by periods!
		    ((looking-at mail-extr-x400-encoded-address-pattern)
		     
		     ;; Copy the contents of the individual fields that
		     ;; might hold name data to the beginning.
		     (mapcar
		      (function
		       (lambda (field-pattern)
			 (cond
			  ((save-excursion
			     (re-search-forward field-pattern nil t))
			   (insert-buffer-substring (current-buffer)
						    (match-beginning 1)
						    (match-end 1))
			   (insert " ")))))
		      (list mail-extr-x400-encoded-address-given-name-pattern
			    mail-extr-x400-encoded-address-surname-pattern
			    mail-extr-x400-encoded-address-full-name-pattern))
		     
		     ;; Discard the rest, since it contains stuff like
		     ;; routing information, not part of a name.
		     (mail-extr-skip-whitespace-backward)
		     (delete-region (point) (point-max))
		     
		     ;; Handle periods used for spacing.
		     (while (re-search-forward mail-extr-bad-dot-pattern nil t)
		       (replace-match "\\1 \\2" t))
		     
;;		     (setq mailbox-name-processed-flag t)
		     )
		    
		    ;; Handle normal addresses.
		    (t
		     (goto-char (point-min))
		     ;; Handle _ and = used for spacing.
		     (while (re-search-forward "\\([^_=]+\\)[_=]" nil t)
		       (replace-match "\\1 " t)
;;		       (setq mailbox-name-processed-flag t)
		       )
		     (goto-char (point-max))))))))

	     ;; undo the dirty deed
	     (if (not mail-extr-mangle-uucp)
		 (modify-syntax-entry ?! "." (syntax-table)))
	     ;;
	     ;; If we derived the name from the mailbox part of the address,
	     ;; and we only got one word out of it, don't treat that as a
	     ;; name.  "foo@bar" --> (nil "foo@bar"), not ("foo" "foo@bar")
             ;; (if (not mailbox-name-processed-flag)
             ;;     (delete-region (point-min) (point-max)))
	     ))
      
      (set-syntax-table mail-extr-address-text-syntax-table)
      
      (mail-extr-voodoo mbox-beg mbox-end canonicalization-buffer)
      (goto-char (point-min))

      ;; If name is "First Last" and userid is "F?L", then assume
      ;; the middle initial is the second letter in the userid.
      ;; Initial code by Jamie Zawinski <jwz@lucid.com>
      ;; *** Make it work when there's a suffix as well.
      (goto-char (point-min))
      (cond ((and mail-extr-guess-middle-initial
		  (not disable-initial-guessing-flag)
		  (eq 3 (- mbox-end mbox-beg))
		  (progn
		    (goto-char (point-min))
		    (looking-at mail-extr-two-name-pattern)))
	     (setq fi (char-after (match-beginning 0))
		   li (char-after (match-beginning 3)))
	     (save-excursion
	       (set-buffer canonicalization-buffer)
	       ;; char-equal is ignoring case here, so no need to upcase
	       ;; or downcase.
	       (let ((case-fold-search t))
		 (and (char-equal fi (char-after mbox-beg))
		      (char-equal li (char-after (1- mbox-end)))
		      (setq mi (char-after (1+ mbox-beg))))))
	     (cond ((and mi
			 ;; TODO: use better table than syntax table
			 (eq ?w (char-syntax mi)))
		    (goto-char (match-beginning 3))
		    (insert (upcase mi) ". ")))))
      
      ;; Nuke name if it is the same as mailbox name.
      (let ((buffer-length (- (point-max) (point-min)))
	    (i 0)
	    (names-match-flag t))
	(cond ((and (> buffer-length 0)
		    (eq buffer-length (- mbox-end mbox-beg)))
	       (goto-char (point-max))
	       (insert-buffer-substring canonicalization-buffer
					mbox-beg mbox-end)
	       (while (and names-match-flag
			   (< i buffer-length))
		 (or (eq (let ((c (char-after (+ i (point-min)))))
			   (if mail-extr-mailbox-match-case-fold
			       (downcase c)
			     c))
			 (downcase
			  (char-after (+ i buffer-length (point-min)))))
		     (setq names-match-flag nil))
		 (setq i (1+ i)))
	       (delete-region (+ (point-min) buffer-length) (point-max))
	       (if names-match-flag
		   (narrow-to-region (point) (point))))))
      
      ;; Nuke name if it's just one word.
      (goto-char (point-min))
      (and mail-extr-ignore-single-names
	   (not (re-search-forward "[- ]" nil t))
	   (narrow-to-region (point) (point)))
      
      ;; Result
      (list (if (not (= (point-min) (point-max)))
		(buffer-string))
	    (progn
	      (set-buffer canonicalization-buffer)
	      (if (not (= (point-min) (point-max)))
		  (buffer-string))))
      )))

(defun mail-extr-voodoo (mbox-beg mbox-end canonicalization-buffer)
  (let ((word-count 0)
	(case-fold-search nil)
	mixed-case-flag lower-case-flag ;;upper-case-flag
	suffix-flag last-name-comma-flag
	;;cbeg cend
	initial
	begin-again-flag
	drop-this-word-if-trailing-flag
	drop-last-word-if-trailing-flag
	word-found-flag
	this-word-beg last-word-beg
	name-beg name-end
	name-done-flag
	)
    (save-excursion
      (set-syntax-table mail-extr-address-text-syntax-table)
      
      ;; This was moved above.
      ;; Fix . used as space
      ;; But it belongs here because it occurs not only as
      ;;   rypens@reks.uia.ac.be (Piet.Rypens)
      ;; but also as
      ;;   "Piet.Rypens" <rypens@reks.uia.ac.be>
      ;;(goto-char (point-min))
      ;;(while (re-search-forward mail-extr-bad-dot-pattern nil t)
      ;;  (replace-match "\\1 \\2" t))

      (cond ((not (search-forward " " nil t))
	     (goto-char (point-min))
	     (cond ((search-forward "_" nil t)
		    ;; Handle the *idiotic* use of underlines as spaces.
		    ;; Example: fml@foo.bar.dom (First_M._Last)
		    (goto-char (point-min))
		    (while (search-forward "_" nil t)
		      (replace-match " " t)))
		   ((search-forward "." nil t)
		    ;; Fix . used as space
		    ;; Example: danj1@cb.att.com (daniel.jacobson)
		    (goto-char (point-min))
		    (while (re-search-forward mail-extr-bad-dot-pattern nil t)
		      (replace-match "\\1 \\2" t))))))


      ;; Loop over the words (and other junk) in the name.
      (goto-char (point-min))
      (while (not name-done-flag)
	
	(cond (word-found-flag
	       ;; Last time through this loop we skipped over a word.
	       (setq last-word-beg this-word-beg)
	       (setq drop-last-word-if-trailing-flag
		     drop-this-word-if-trailing-flag)
	       (setq word-found-flag nil)))

	(cond (begin-again-flag
	       ;; Last time through the loop we found something that
	       ;; indicates we should pretend we are beginning again from
	       ;; the start.
	       (setq word-count 0)
	       (setq last-word-beg nil)
	       (setq drop-last-word-if-trailing-flag nil)
	       (setq mixed-case-flag nil)
	       (setq lower-case-flag nil)
;;	       (setq upper-case-flag nil)
	       (setq begin-again-flag nil)
	       ))
	
	;; Initialize for this iteration of the loop.
	(mail-extr-skip-whitespace-forward)
	(if (eq word-count 0) (narrow-to-region (point) (point-max)))
	(setq this-word-beg (point))
	(setq drop-this-word-if-trailing-flag nil)
	
	;; Decide what to do based on what we are looking at.
	(cond
	 
	 ;; Delete title
	 ((and (eq word-count 0)
	       (looking-at mail-extr-full-name-prefixes))
	  (goto-char (match-end 0))
	  (narrow-to-region (point) (point-max)))
	 
	 ;; Stop after name suffix
	 ((and (>= word-count 2)
	       (looking-at mail-extr-full-name-suffix-pattern))
	  (mail-extr-skip-whitespace-backward)
	  (setq suffix-flag (point))
	  (if (eq ?, (char-after))
	      (forward-char 1)
	    (insert ?,))
	  ;; Enforce at least one space after comma
	  (or (eq ?\  (char-after))
	      (insert ?\ ))
	  (mail-extr-skip-whitespace-forward)
	  (cond ((memq (char-after) '(?j ?J ?s ?S))
		 (capitalize-word 1)
		 (if (eq (char-after) ?.)
		     (forward-char 1)
		   (insert ?.)))
		(t
		 (upcase-word 1)))
	  (setq word-found-flag t)
	  (setq name-done-flag t))
	 
	 ;; Handle SCA names
	 ((looking-at "MKA \\(.+\\)")	; "Mundanely Known As"
	  (goto-char (match-beginning 1))
	  (narrow-to-region (point) (point-max))
	  (setq begin-again-flag t))
	 
	 ;; Check for initial last name followed by comma
	 ((and (eq ?, (char-after))
	       (eq word-count 1))
	  (forward-char 1)
	  (setq last-name-comma-flag t)
	  (or (eq ?\  (char-after))
	      (insert ?\ )))

	 ;; Stop before trailing comma-separated comment
	 ;; THIS CASE MUST BE AFTER THE PRECEDING CASES.
	 ;; *** This case is redundant???
	 ;;((eq ?, (char-after))
	 ;; (setq name-done-flag t))
	 
	 ;; Delete parenthesized/quoted comment/nickname
	 ((memq (char-after) '(?\( ?\{ ?\[ ?\" ?\' ?\`))
	  (setq cbeg (point))
	  (set-syntax-table mail-extr-address-text-comment-syntax-table)
	  (cond ((memq (char-after) '(?\' ?\`))
		 (or (search-forward "'" nil t
				     (if (eq ?\' (char-after)) 2 1))
		     (mail-extr-delete-char 1)))
		(t
		 (or (mail-extr-safe-move-sexp 1)
		     (goto-char (point-max)))))
	  (set-syntax-table mail-extr-address-text-syntax-table)
	  (setq cend (point))
	  (cond
	   ;; Handle case of entire name being quoted
	   ((and (eq word-count 0)
		 (looking-at " *\\'")
		 (>= (- cend cbeg) 2))
	    (narrow-to-region (1+ cbeg) (1- cend))
	    (goto-char (point-min)))
	   (t
	    ;; Handle case of quoted initial
	    (if (and (or (= 3 (- cend cbeg))
			 (and (= 4 (- cend cbeg))
			      (eq ?. (char-after (+ 2 cbeg)))))
		     (not (looking-at " *\\'")))
		(setq initial (char-after (1+ cbeg)))
	      (setq initial nil))
	    (delete-region cbeg cend)
	    (if initial
		(insert initial ". ")))))
	 
	 ;; Handle & substitution
	 ((and (or (bobp)
		   (eq ?\  (char-before)))
	       (looking-at "&\\( \\|\\'\\)"))
	  (mail-extr-delete-char 1)
	  (capitalize-region
	   (point)
	   (progn
	     (insert-buffer-substring canonicalization-buffer
				      mbox-beg mbox-end)
	     (point)))
	  (setq disable-initial-guessing-flag t)
	  (setq word-found-flag t))
	 
	 ;; Handle *Stupid* VMS date stamps
	 ((looking-at mail-extr-stupid-vms-date-stamp-pattern)
	  (replace-match "" t))

	 ;; Handle Chinese characters.
	 ((looking-at mail-extr-hz-embedded-gb-encoded-chinese-pattern)
	  (goto-char (match-end 0))
	  (setq word-found-flag t))
	 
	 ;; Skip initial garbage characters.
	 ;; THIS CASE MUST BE AFTER THE PRECEDING CASES.
	 ((and (eq word-count 0)
	       (looking-at mail-extr-leading-garbage))
	  (goto-char (match-end 0))
	  ;; *** Skip backward over these???
	  ;; (skip-chars-backward "& \"")
	  (narrow-to-region (point) (point-max)))
	 
	 ;; Various stopping points
	 ((or
	   
	   ;; Stop before ALL CAPS acronyms, if preceded by mixed-case
	   ;; words.  Example: XT-DEM.
	   (and (>= word-count 2)
		mixed-case-flag
		(looking-at mail-extr-weird-acronym-pattern)
		(not (looking-at mail-extr-roman-numeral-pattern)))
	   
	   ;; Stop before trailing alternative address
	   (looking-at mail-extr-alternative-address-pattern)
	   
	   ;; Stop before trailing comment not introduced by comma
	   ;; THIS CASE MUST BE AFTER AN EARLIER CASE.
	   (looking-at mail-extr-trailing-comment-start-pattern)
	   
	   ;; Stop before telephone numbers
	   (looking-at mail-extr-telephone-extension-pattern))
	  (setq name-done-flag t))
	 
	 ;; Delete ham radio call signs
	 ((looking-at mail-extr-ham-call-sign-pattern)
	  (delete-region (match-beginning 0) (match-end 0)))
	 
	 ;; Fixup initials
	 ((looking-at mail-extr-initial-pattern)
	  (or (eq (char-after) (upcase (char-after)))
	      (setq lower-case-flag t))
	  (forward-char 1)
	  (if (eq ?. (char-after))
	      (forward-char 1)
	    (insert ?.))
	  (or (eq ?\  (char-after))
	      (insert ?\ ))
	  (setq word-found-flag t))

	 ;; Handle BITNET LISTSERV list names.
	 ((and (eq word-count 0)
	       (looking-at mail-extr-listserv-list-name-pattern))
	  (narrow-to-region (match-beginning 1) (match-end 1))
	  (setq word-found-flag t)
	  (setq name-done-flag t))

	 ;; Regular name words
	 ((looking-at mail-extr-name-pattern)
	  (setq name-beg (point))
	  (setq name-end (match-end 0))

	  ;; Certain words will be dropped if they are at the end.
	  (and (>= word-count 2)
	       (not lower-case-flag)
	       (or
		;; A trailing 4-or-more letter lowercase words preceded by
		;; mixed case or uppercase words will be dropped.
		(looking-at "[a-z][a-z][a-z][a-z]+[ \t]*\\'")
		;; Drop a trailing word which is terminated with a period.
		(eq ?. (char-after (1- name-end))))
	       (setq drop-this-word-if-trailing-flag t))
	  
	  ;; Set the flags that indicate whether we have seen a lowercase
	  ;; word, a mixed case word, and an uppercase word.
	  (if (re-search-forward "[a-z]" name-end t)
	      (if (progn
		    (goto-char name-beg)
		    (re-search-forward "[A-Z]" name-end t))
		  (setq mixed-case-flag t)
		(setq lower-case-flag t))
;;	    (setq upper-case-flag t)
	    )
	  
	  (goto-char name-end)
	  (setq word-found-flag t))

	 (t
	  (setq name-done-flag t)
	  ))
	
	;; Count any word that we skipped over.
	(if word-found-flag
	    (setq word-count (1+ word-count))))
      
      ;; If the last thing in the name is 2 or more periods, or one or more
      ;; other sentence terminators (but not a single period) then keep them
      ;; and the preceding word.  This is for the benefit of whole sentences
      ;; in the name field: it's better behavior than dropping the last word
      ;; of the sentence...
      (if (and (not suffix-flag)
	       (looking-at "\\(\\.+\\|[?!;:.][?!;:.]+\\|[?!;:][?!;:.]*\\)\\'"))
	  (goto-char (setq suffix-flag (point-max))))

      ;; Drop everything after point and certain trailing words.
      (narrow-to-region (point-min)
			(or (and drop-last-word-if-trailing-flag
				 last-word-beg)
			    (point)))
      
      ;; Xerox's mailers SUCK!!!!!!
      ;; We simply refuse to believe that any last name is PARC or ADOC.
      ;; If it looks like that is the last name, that there is no meaningful
      ;; here at all.  Actually I guess it would be best to map patterns
      ;; like foo.hoser@xerox.com into foo@hoser.xerox.com, but I don't
      ;; actually know that that is what's going on.
      (cond ((not suffix-flag)
	     (goto-char (point-min))
	     (let ((case-fold-search t))
	       (if (looking-at "[-A-Za-z_]+[. ]\\(PARC\\|ADOC\\)\\'")
		   (erase-buffer)))))

      ;; If last name first put it at end (but before suffix)
      (cond (last-name-comma-flag
	     (goto-char (point-min))
	     (search-forward ",")
	     (setq name-end (1- (point)))
	     (goto-char (or suffix-flag (point-max)))
	     (or (eq ?\  (char-before))
		 (insert ?\ ))
	     (insert-buffer-substring (current-buffer) (point-min) name-end)
	     (goto-char name-end)
	     (skip-chars-forward "\t ,")
	     (narrow-to-region (point) (point-max))))
      
      ;; Delete leading and trailing junk characters.
      ;; *** This is probably completly unneeded now.
      ;;(goto-char (point-max))
      ;;(skip-chars-backward mail-extr-non-end-name-chars)
      ;;(if (eq ?. (char-after))
      ;;    (forward-char 1))
      ;;(narrow-to-region (point)
      ;;                  (progn
      ;;                    (goto-char (point-min))
      ;;                    (skip-chars-forward mail-extr-non-begin-name-chars)
      ;;                    (point)))
      
      ;; Compress whitespace
      (goto-char (point-min))
      (while (re-search-forward "[ \t\n]+" nil t)
	(replace-match (if (eobp) "" " ") t))
      )))



;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; Table of top-level domain names.
;;
;; This is used during address canonicalization; be careful of format changes.
;; Keep in mind that the country abbreviations follow ISO-3166.  There is
;; a U.S. FIPS that specifies a different set of two-letter country
;; abbreviations.
;;
;; Two letter country codes synched with
;; http://www.iana.org/in-notes/iana/assignments/country-codes
;;
;; Updated by the RIPE Network Coordination Centre.
;;
;; Source: ISO 3166 Maintenance Agency 
;; Latest change: Thu Aug  7 17:59:51 MET DST 1997

(defconst all-top-level-domains
  (let ((ob (make-vector 509 0)))
    (mapcar
     (function
      (lambda (x)
	(put (intern (downcase (car x)) ob)
	     'domain-name
	     (if (nth 2 x)
		 (format (nth 2 x) (nth 1 x))
	       (nth 1 x)))))
     '(("ad" "Andorra")
       ("ae" "United Arab Emirates")
       ("af" "Afghanistan")
       ("ag" "Antigua")
       ("ai" "Anguilla")
       ("al" "Albania")
       ("am" "Armenia")
       ("an" "Netherlands Antilles")
       ("aq" "Antarctica")
       ("ar" "Argentina"	"Argentine Republic")
       ("arpa" t		"Advanced Projects Research Agency")
       ("as" "American Samoa")
       ("at" "Austria"		"The Republic of %s")
       ("au" "Australia")
       ("aw" "Aruba")
       ("az" "Azerbaijan")
       ("ba" "Bosnia-Herzegovina")
       ("bb" "Barbados")
       ("bd" "Bangladesh")
       ("be" "Belgium"		"The Kingdom of %s")
       ("bf" "Burkina Faso")
       ("bg" "Bulgaria")
       ("bh" "Bahrain")
       ("bi" "Burundi")
       ("bitnet" t		"Because It's Time NET")
       ("bj" "Benin")
       ("bm" "Bermuda")
       ("bn" "Brunei Darussalam")
       ("bo" "Bolivia"		"Republic of %s")
       ("br" "Brazil"		"The Federative Republic of %s")
       ("bs" "Bahamas")
       ("bt" "Bhutan")
       ("bv" "Bouvet Island")
       ("bw" "Botswana")
       ("by" "Belarus")
       ("bz" "Belize")
       ("ca" "Canada")
       ("cc" "Cocos (Keeling) Islands")
       ("cd" "Congo"            "The Democratic Republic of the %s")
       ("cf" "Central African Republic")
       ("cg" "Congo")
       ("ch" "Switzerland"	"The Swiss Confederation")
       ("ci" "Cote D'Ivoire")
       ("ck" "Cook Islands")
       ("cl" "Chile"		"The Republic of %s")
       ("cm" "Cameroon")
       ("cn" "China"		"The People's Republic of %s")
       ("co" "Columbia")
       ("com" t			"Commercial")
       ("cr" "Costa Rica"	"The Republic of %s")
       ("cu" "Cuba")
       ("cv" "Cape Verde")
       ("cx" "Christmas Island")
       ("cy" "Cyprus")
       ("cz" "Czech Republic")
       ("de" "Germany")
       ("dj" "Djibouti")
       ("dk" "Denmark")
       ("dm" "Dominica")
       ("do" "Dominican Republic"	"The %s")
       ("dz" "Algeria")
       ("ec" "Ecuador"		"The Republic of %s")
       ("edu" t			"Educational")
       ("ee" "Estonia")
       ("eg" "Egypt"		"The Arab Republic of %s")
       ("eh" "Western Sahara")
       ("er" "Eritrea")
       ("es" "Spain"		"The Kingdom of %s")
       ("et" "Ethiopia")
       ("fi" "Finland"		"The Republic of %s")
       ("fj" "Fiji")
       ("fk" "Falkland Islands (Malvinas)")
       ("fm" "Micronesia"       "The Federated States of %s")
       ("fo" "Faroe Islands")
       ("fr" "France")
       ("fx" "France (metropolitan)")
       ("ga" "Gabon")
       ("gb" "United Kingdom")
       ("gd" "Grenada")
       ("ge" "Georgia")
       ("gf" "French Guiana")
       ("gh" "Ghana")
       ("gi" "Gibraltar")
       ("gl" "Greenland")
       ("gm" "Gambia")
       ("gn" "Guinea")
       ("gov" t			"Government (U.S.A.)")
       ("gp" "Guadeloupe")
       ("gq" "Equatorial Guinea")
       ("gr" "Greece"		"The Hellenic Republic (%s)")
       ("gs" "South Georgia and the South Sandwich Islands")
       ("gt" "Guatemala")
       ("gu" "Guam")
       ("gw" "Guinea-Bissau")
       ("gy" "Guyana")
       ("hk" "Hong Kong")
       ("hm" "Heard and McDonald Islands")                     
       ("hn" "Honduras")
       ("hr" "Croatia"         "The Republic of Croatia")
       ("ht" "Haiti")
       ("hu" "Hungary"		"The Hungarian People's Republic")
       ("id" "Indonesia")
       ("ie" "Ireland")
       ("il" "Israel"		"The State of %s")
       ("im" "Isle of Man"	"The %s")
       ("in" "India"		"The Republic of %s")
       ("int" t			"International")
       ;("int" t			"(something British, don't know what)")
       ("io" "British Indian Ocean Territory")
       ("iq" "Iraq")
       ("ir" "Iran"             "The Islamic Republic of %s")
       ("is" "Iceland"		"The Republic of %s")
       ("it" "Italy"		"The Italian Republic")
       ("jm" "Jamaica")
       ("jo" "Jordan")
       ("jp" "Japan")
       ("ke" "Kenya")
       ("kg" "Kyrgyzstan")
       ("kh" "Cambodia")
       ("ki" "Kiribati")
       ("km" "Comoros")
       ("kn" "St. Kitts and Nevis")
       ("kp" "Korea"            "The Democratic People's Republic of %s")
       ("kr" "Korea"            "The Republic of %s")
       ("kw" "Kuwait")
       ("ky" "Cayman Islands")
       ("kz" "Kazakhstan")
       ("la" "Lao"              "The People's Democratic Republic of %s")
       ("lb" "Lebanon")
       ("lc" "St. Lucia")
       ("li" "Liechtenstein")
       ("lk" "Sri Lanka"	"The Democratic Socialist Republic of %s")
       ("lr" "Liberia")
       ("ls" "Lesotho")
       ("lt" "Lithuania")
       ("lu" "Luxembourg")
       ("lv" "Latvia")
       ("ly" "Libyan Arab Jamahiriya")
       ("mc" "Monaco")
       ("md" "Moldova"		"The Republic of %s")
       ("mg" "Madagascar")
       ("mh" "Marshall Islands")
       ("mil" t			"Military (U.S.A.)")
       ("mk" "Macedonia"        "The former Yugoslav Republic of %s")
       ("ml" "Mali")
       ("mm" "Myanmar")
       ("mn" "Mongolia")
       ("mo" "Macau")
       ("mp" "Northern Mariana Islands")
       ("mq" "Martinique")
       ("mr" "Mauritania")
       ("ms" "Montserrat")
       ("mt" "Malta")
       ("mu" "Mauritius")
       ("mv" "Maldives")
       ("mw" "Malawi")
       ("mx" "Mexico"		"The United Mexican States")
       ("my" "Malaysia")
       ("mz" "Mozambique")
       ("na" "Namibia")
       ("nato" t		"North Atlantic Treaty Organization")
       ("nc" "New Caledonia")
       ("ne" "Niger")
       ("net" t			"Network")
       ("nf" "Norfolk Island")
       ("ng" "Nigeria")
       ("ni" "Nicaragua"	"The Republic of %s")
       ("nl" "Netherlands"	"The Kingdom of the %s")
       ("no" "Norway"		"The Kingdom of %s")
       ("np" "Nepal")
       ("nr" "Nauru")
       ("nu" "Niue")
       ("nz" "New Zealand")
       ("om" "Oman")
       ("org" t			"Organization")
       ("pa" "Panama")
       ("pe" "Peru")
       ("pf" "French Polynesia")
       ("pg" "Papua New Guinea")
       ("ph" "Philippines"	"The Republic of the %s")
       ("pk" "Pakistan")
       ("pl" "Poland")
       ("pm" "St. Pierre and Miquelon")
       ("pn" "Pitcairn")
       ("pr" "Puerto Rico")
       ("pt" "Portugal"		"The Portugese Republic")
       ("pw" "Palau")
       ("py" "Paraguay")
       ("qa" "Qatar")
       ("re" "Reunion")
       ("ro" "Romania")
       ("ru" "Russian Federation")
       ("rw" "Rwanda")
       ("sa" "Saudi Arabia")
       ("sb" "Solomon Islands")
       ("sc" "Seychelles")
       ("sd" "Sudan")
       ("se" "Sweden"		"The Kingdom of %s")
       ("sg" "Singapore"	"The Republic of %s")
       ("sh" "St. Helena")
       ("si" "Slovenia")
       ("sj" "Svalbard and Jan Mayen Islands")
       ("sk" "Slovakia"		"The Slovak Republic")
       ("sl" "Sierra Leone")
       ("sm" "San Marino")
       ("sn" "Senegal")
       ("so" "Somalia")
       ("sr" "Suriname")
       ("st" "Sao Tome and Principe")
       ("su" "U.S.S.R."		"The Union of Soviet Socialist Republics")
       ("sv" "El Salvador")
       ("sy" "Syrian Arab Republic")
       ("sz" "Swaziland")
       ("tc" "Turks and Caicos Islands")
       ("td" "Chad")
       ("tf" "French Southern Territories")
       ("tg" "Togo")
       ("th" "Thailand"		"The Kingdom of %s")
       ("tj" "Tajikistan")
       ("tk" "Tokelau")
       ("tm" "Turkmenistan")
       ("tn" "Tunisia")
       ("to" "Tonga")
       ("tp" "East Timor")
       ("tr" "Turkey"		"The Republic of %s")
       ("tt" "Trinidad and Tobago")
       ("tv" "Tuvalu")
       ("tw" "Taiwan")
       ("tz" "Tanzania"         "The United Republic of %s")
       ("ua" "Ukraine")
       ("ug" "Uganda")
       ("uk" "United Kingdom"	"The %s of Great Britain")
       ("um" "United States Minor Outlying Islands")
       ("unter-dom" t		"(something German)")
       ("us" "U.S.A."		"The United States of America")
       ("uucp" t		"Unix to Unix CoPy")
       ("uy" "Uruguay"		"The Eastern Republic of %s")
       ("uz" "Uzbekistan")
       ("va" "Holy See (Vatican City State)")
       ("vc" "St. Vincent and the Grenadines")
       ("ve" "Venezuela"	"The Republic of %s")
       ("vg" "Virgin Islands (British)")
       ("vi" "Virgin Islands (U.S.A.)")
       ("vn" "Viet Nam")
       ("vu" "Vanuatu")
       ("wf" "Wallis and Futuna Islands")
       ("ws" "Samoa")
       ("ye" "Yemen")
       ("yt" "Mayotte")
       ("yu" "Yugoslavia"	"Yugoslavia, AKA Serbia-Montenegro")
       ("za" "South Africa"	"The Republic of %s")
       ("zm" "Zambia")
       ("zw" "Zimbabwe"		"Republic of %s")
;; fipnet
       ))
    ob))

;;;###autoload
(defun what-domain (x)
  "Prompts for a mail domain, and prints the country it corresponds to
in the minibuffer."
  (interactive
   (let ((completion-ignore-case t))
     (list (completing-read "Domain: " all-top-level-domains nil t))))
  (or (setq x (intern-soft (downcase x) all-top-level-domains))
      (error "no such domain"))
  (message "%s: %s" (upcase (symbol-name x)) (get x 'domain-name)))


;(let ((all nil))
;  (mapatoms #'(lambda (x)
;		(if (and (boundp x) 
;			 (string-match "^mail-extr-" (symbol-name x)))
;		    (setq all (cons x all)))))
;  (setq all (sort all #'string-lessp))
;  (cons 'setq
;	(apply 'nconc (mapcar #'(lambda (x)
;				  (list x (symbol-value x)))
;			      all))))


(provide 'mail-extr)

;;; mail-extr.el ends here
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.