lisp/mh-e/mh-scan.el

   1 ;;; mh-scan.el --- MH-E scan line constants and utilities
   2
   3 ;; Copyright (C) 1993, 1995, 1997, 2000-2018 Free Software Foundation,
   4 ;; Inc.
   5
   6 ;; Author: Bill Wohler <wohler@newt.com>
   7 ;; Maintainer: Bill Wohler <wohler@newt.com>
   8 ;; Keywords: mail
   9 ;; See: mh-e.el
  10
  11 ;; This file is part of GNU Emacs.
  12
  13 ;; GNU Emacs is free software: you can redistribute it and/or modify
  14 ;; it under the terms of the GNU General Public License as published by
  15 ;; the Free Software Foundation, either version 3 of the License, or
  16 ;; (at your option) any later version.
  17
  18 ;; GNU Emacs is distributed in the hope that it will be useful,
  19 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21 ;; GNU General Public License for more details.
  22
  23 ;; You should have received a copy of the GNU General Public License
  24 ;; along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.
  25
  26 ;;; Commentary:
  27
  28 ;; This file contains constants and a few functions for interpreting
  29 ;; scan lines.
  30
  31 ;;; Change Log:
  32
  33 ;;; Code:
  34
  35 (require 'mh-e)
  36
  37 \f
  38
  39 ;;; Scan Formats
  40
  41 ;; The following scan formats are passed to the scan program if the setting of
  42 ;; `mh-scan-format-file' is t. They are identical except the later one makes
  43 ;; use of the nmh `decode' function to decode RFC 2047 encodings. If you just
  44 ;; want to change the column of the notations, use the `mh-set-cmd-note'
  45 ;; function.
  46
  47 (defcustom mh-scan-format-mh
  48   (concat
  49    "%4(msg)"
  50    "%<(cur)+%| %>"
  51    "%<{replied}-"
  52    "%?(nonnull(comp{to}))%<(mymbox{to})t%>"
  53    "%?(nonnull(comp{cc}))%<(mymbox{cc})c%>"
  54    "%?(nonnull(comp{bcc}))%<(mymbox{bcc})b%>"
  55    "%?(nonnull(comp{newsgroups}))n%>"
  56    "%<(zero) %>"
  57    "%02(mon{date})/%02(mday{date})%<{date} %|*%>"
  58    "%<(mymbox{from})%<{to}To:%14(friendly{to})%>%>"
  59    "%<(zero)%17(friendly{from})%>  "
  60    "%{subject}%<{body}<<%{body}%>")
  61   "Scan format string for MH.
  62 This string is passed to the scan program via the -format
  63 argument.  This format is identical to the default except that
  64 additional hints for fontification have been added to the fifth
  65 column (remember that in Emacs, the first column is 0).
  66
  67 The values of the fifth column, in priority order, are: \"-\" if
  68 the message has been replied to, t if an address on the To: line
  69 matches one of the mailboxes of the current user, \"c\" if the Cc:
  70 line matches, \"b\" if the Bcc: line matches, and \"n\" if a
  71 non-empty Newsgroups: header is present."
  72   :group 'mh-scan-line-formats
  73   :type 'string)
  74
  75 (defcustom mh-scan-format-nmh
  76   (concat
  77    "%4(msg)"
  78    "%<(cur)+%| %>"
  79    "%<{replied}-"
  80    "%?(nonnull(comp{to}))%<(mymbox{to})t%>"
  81    "%?(nonnull(comp{cc}))%<(mymbox{cc})c%>"
  82    "%?(nonnull(comp{bcc}))%<(mymbox{bcc})b%>"
  83    "%?(nonnull(comp{newsgroups}))n%>"
  84    "%<(zero) %>"
  85    "%02(mon{date})/%02(mday{date})%<{date} %|*%>"
  86    "%<(mymbox{from})%<{to}To:%14(decode(friendly{to}))%>%>"
  87    "%<(zero)%17(decode(friendly{from}))%>  "
  88    "%(decode{subject})%<{body}<<%{body}%>")
  89   "Scan format string for nmh.
  90 This string is passed to the scan program via the -format arg.
  91 This format is identical to the default except that additional
  92 hints for fontification have been added to the fifth
  93 column (remember that in Emacs, the first column is 0).
  94
  95 The values of the fifth column, in priority order, are: \"-\" if
  96 the message has been replied to, t if an address on the To: field
  97 matches one of the mailboxes of the current user, \"c\" if the Cc:
  98 field matches, \"b\" if the Bcc: field matches, and \"n\" if a
  99 non-empty Newsgroups: field is present."
 100   :group 'mh-scan-line-formats
 101   :type 'string)
 102
 103 \f
 104
 105 ;;; Regular Expressions
 106
 107 ;; Alphabetical.
 108
 109 (defvar mh-scan-body-regexp "\\(<<\\([^\n]+\\)?\\)"
 110   "This regular expression matches the message body fragment.
 111
 112 Note that the default setting of `mh-folder-font-lock-keywords'
 113 expects this expression to contain at least one parenthesized
 114 expression which matches the body text as in the default of
 115 \"\\\\(<<\\\\([^\\n]+\\\\)?\\\\)\".  If this regular expression is
 116 not correct, the body fragment will not be highlighted with the
 117 face `mh-folder-body'.")
 118
 119 (defvar mh-scan-blacklisted-msg-regexp "^\\( *[0-9]+\\)B"
 120   "This regular expression matches blacklisted (spam) messages.
 121
 122 It must match from the beginning of the line. Note that the
 123 default setting of `mh-folder-font-lock-keywords' expects this
 124 expression to contain at least one parenthesized expression which
 125 matches the message number as in the default of
 126
 127   \"^\\\\( *[0-9]+\\\\)B\".
 128
 129 This expression includes the leading space within parenthesis
 130 since it looks better to highlight it as well. The highlighting
 131 is done with the face `mh-folder-blacklisted'. This regular
 132 expression should be correct as it is needed by non-fontification
 133 functions. See also `mh-note-blacklisted'.")
 134
 135 (defvar mh-scan-cur-msg-number-regexp "^\\( *[0-9]+\\+\\).*"
 136   "This regular expression matches the current message.
 137
 138 It must match from the beginning of the line.  Note that the
 139 default setting of `mh-folder-font-lock-keywords' expects this
 140 expression to contain at least one parenthesized expression which
 141 matches the message number as in the default of
 142
 143   \"^\\\\( *[0-9]+\\\\+\\\\).*\".
 144
 145 This expression includes the leading space and current message
 146 marker \"+\" within the parenthesis since it looks better to
 147 highlight these items as well.  The highlighting is done with the
 148 face `mh-folder-cur-msg-number'.  This regular expression should
 149 be correct as it is needed by non-fontification functions.  See
 150 also `mh-note-cur'.")
 151
 152 (defvar mh-scan-date-regexp "\\([0-9][0-9]/[0-9][0-9]\\)"
 153   "This regular expression matches a valid date.
 154
 155 It must not be anchored to the beginning or the end of the line.
 156 Note that the default setting of `mh-folder-font-lock-keywords'
 157 expects this expression to contain only one parenthesized
 158 expression which matches the date field as in the default of
 159 \"\\\\([0-9][0-9]/[0-9][0-9]\\\\)\"}.  If this regular expression
 160 is not correct, the date will not be highlighted with the face
 161 `mh-folder-date'.")
 162
 163 (defvar mh-scan-deleted-msg-regexp "^\\( *[0-9]+\\)D"
 164   "This regular expression matches deleted messages.
 165
 166 It must match from the beginning of the line.  Note that the
 167 default setting of `mh-folder-font-lock-keywords' expects this
 168 expression to contain at least one parenthesized expression which
 169 matches the message number as in the default of
 170
 171   \"^\\\\( *[0-9]+\\\\)D\".
 172
 173 This expression includes the leading space within the parenthesis
 174 since it looks better to highlight it as well.  The highlighting
 175 is done with the face `mh-folder-deleted'.  This regular
 176 expression should be correct as it is needed by non-fontification
 177 functions.  See also `mh-note-deleted'.")
 178
 179 (defvar mh-scan-good-msg-regexp  "^\\( *[0-9]+\\)[^^DBW0-9]"
 180   "This regular expression matches \"good\" messages.
 181
 182 It must match from the beginning of the line.  Note that the
 183 default setting of `mh-folder-font-lock-keywords' expects this
 184 expression to contain at least one parenthesized expression which
 185 matches the message number as in the default of
 186
 187   \"^\\\\( *[0-9]+\\\\)[^^DBW0-9]\".
 188
 189 This expression includes the leading space within the parenthesis
 190 since it looks better to highlight it as well.  The highlighting
 191 is done with the face `mh-folder-msg-number'.  This regular
 192 expression should be correct as it is needed by non-fontification
 193 functions.")
 194
 195 (defvar mh-scan-msg-format-regexp "%\\([0-9]*\\)(msg)"
 196   "This regular expression finds the message number width in a scan format.
 197
 198 Note that the message number must be placed in a parenthesized
 199 expression as in the default of \"%\\\\([0-9]*\\\\)(msg)\".  This
 200 variable is only consulted if `mh-scan-format-file' is set to
 201 \"Use MH-E scan Format\".")
 202
 203 (defvar mh-scan-msg-format-string "%d"
 204   "This is a format string for width of the message number in a scan format.
 205
 206 Use \"0%d\" for zero-filled message numbers.  This variable is only
 207 consulted if `mh-scan-format-file' is set to \"Use MH-E scan
 208 Format\".")
 209
 210 (defvar mh-scan-msg-number-regexp "^ *\\([0-9]+\\)"
 211   "This regular expression extracts the message number.
 212
 213 It must match from the beginning of the line.  Note that the
 214 message number must be placed in a parenthesized expression as in
 215 the default of \"^ *\\\\([0-9]+\\\\)\".")
 216
 217 (defvar mh-scan-msg-overflow-regexp "^[?0-9][0-9]"
 218   "This regular expression matches overflowed message numbers.")
 219
 220 (defvar mh-scan-msg-search-regexp "^[^0-9]*%d[^0-9]"
 221   "This regular expression matches a particular message.
 222
 223 It is a format string; use \"%d\" to represent the location of the
 224 message number within the expression as in the default of
 225 \"^[^0-9]*%d[^0-9]\".")
 226
 227 (defvar mh-scan-rcpt-regexp  "\\(To:\\)\\(..............\\)"
 228   "This regular expression specifies the recipient in messages you sent.
 229
 230 Note that the default setting of `mh-folder-font-lock-keywords'
 231 expects this expression to contain two parenthesized expressions.
 232 The first is expected to match the \"To:\" that the default scan
 233 format file generates.  The second is expected to match the
 234 recipient's name as in the default of
 235 \"\\\\(To:\\\\)\\\\(..............\\\\)\".  If this regular
 236 expression is not correct, the \"To:\" string will not be
 237 highlighted with the face `mh-folder-to' and the recipient will
 238 not be highlighted with the face `mh-folder-address'")
 239
 240 (defvar mh-scan-refiled-msg-regexp  "^\\( *[0-9]+\\)\\^"
 241   "This regular expression matches refiled messages.
 242
 243 It must match from the beginning of the line.  Note that the
 244 default setting of `mh-folder-font-lock-keywords' expects this
 245 expression to contain at least one parenthesized expression which
 246 matches the message number as in the default of
 247
 248   \"^\\\\( *[0-9]+\\\\)\\\\^\".
 249
 250 This expression includes the leading space within the parenthesis
 251 since it looks better to highlight it as well.  The highlighting
 252 is done with the face `mh-folder-refiled'.  This regular
 253 expression should be correct as it is needed by non-fontification
 254 functions.  See also `mh-note-refiled'.")
 255
 256 (defvar mh-scan-sent-to-me-sender-regexp
 257   "^ *[0-9]+.\\([bct]\\).....[ ]*\\(..................\\)"
 258   "This regular expression matches messages sent to us.
 259
 260 Note that the default setting of `mh-folder-font-lock-keywords'
 261 expects this expression to contain at least two parenthesized
 262 expressions.  The first should match the fontification hint (see
 263 `mh-scan-format-nmh') and the second should match the user name
 264 as in the default of
 265
 266   ^ *[0-9]+.\\\\([bct]\\\\).....[ ]*\\\\(..................\\\\)
 267
 268 If this regular expression is not correct, the notation hints
 269 will not be highlighted with the face
 270 `mh-mh-folder-sent-to-me-hint' and the sender will not be
 271 highlighted with the face `mh-folder-sent-to-me-sender'.")
 272
 273 (defvar mh-scan-subject-regexp
 274   "^ *[0-9]+........[ ]*...................\\([Rr][Ee]\\(\\[[0-9]+\\]\\)?:\\s-*\\)*\\([^<\n]*\\)"
 275   "This regular expression matches the subject.
 276
 277 It must match from the beginning of the line.  Note that the
 278 default setting of `mh-folder-font-lock-keywords' expects this
 279 expression to contain at least three parenthesized expressions.
 280 The first is expected to match the \"Re:\" string, if any, and is
 281 highlighted with the face `mh-folder-followup'.  The second
 282 matches an optional bracketed number after \"Re:\", such as in
 283 \"Re[2]:\" (and is thus a sub-expression of the first expression)
 284 and the third is expected to match the subject line itself which
 285 is highlighted with the face `mh-folder-subject'.  For example,
 286 the default (broken on multiple lines for readability) is
 287
 288   ^ *[0-9]+........[ ]*...................
 289   \\\\([Rr][Ee]\\\\(\\\\\\=[[0-9]+\\\\]\\\\)?:\\\\s-*\\\\)*
 290   \\\\([^<\\n]*\\\\)
 291
 292 This regular expression should be correct as it is needed by
 293 non-fontification functions.")
 294
 295 (defvar mh-scan-valid-regexp "^ *[0-9]"
 296   "This regular expression describes a valid scan line.
 297
 298 This is used to eliminate error messages that are occasionally
 299 produced by \"inc\".")
 300
 301 (defvar mh-scan-whitelisted-msg-regexp "^\\( *[0-9]+\\)W"
 302   "This regular expression matches whitelisted (non-spam) messages.
 303
 304 It must match from the beginning of the line. Note that the
 305 default setting of `mh-folder-font-lock-keywords' expects this
 306 expression to contain at least one parenthesized expression which
 307 matches the message number as in the default of
 308
 309   \"^\\\\( *[0-9]+\\\\)W\".
 310
 311 This expression includes the leading space within parenthesis
 312 since it looks better to highlight it as well. The highlighting
 313 is done with the face `mh-folder-whitelisted'. This regular
 314 expression should be correct as it is needed by non-fontification
 315 functions. See also `mh-note-whitelisted'.")
 316
 317 \f
 318
 319 ;;; Widths, Offsets and Columns
 320
 321 (defvar mh-cmd-note 4
 322   "Column for notations.
 323
 324 This variable should be set with the function `mh-set-cmd-note'.
 325 This variable may be updated dynamically if
 326 `mh-adaptive-cmd-note-flag' is on.
 327
 328 Note that columns in Emacs start with 0.")
 329 (make-variable-buffer-local 'mh-cmd-note)
 330
 331 (defvar mh-scan-cmd-note-width 1
 332   "Number of columns consumed by the cmd-note field in `mh-scan-format'.
 333
 334 This column will have one of the values: \" \", \"^\", \"D\", \"B\", \"W\", \"+\", where
 335
 336   \" \" is the default value,
 337   \"^\" is the `mh-note-refiled' character,
 338   \"D\" is the `mh-note-deleted' character,
 339   \"B\" is the `mh-note-blacklisted' character,
 340   \"W\" is the `mh-note-whitelisted' character, and
 341   \"+\" is the `mh-note-cur' character.")
 342
 343 (defvar mh-scan-destination-width 1
 344   "Number of columns consumed by the destination field in `mh-scan-format'.
 345
 346 This column will have one of \" \", \"%\", \"-\", \"t\", \"c\", \"b\", or \"n\"
 347 in it.
 348
 349   \" \" blank space is the default character.
 350   \"%\" indicates that the message in a named MH sequence.
 351   \"-\" indicates that the message has been annotated with a replied field.
 352   \"t\" indicates that the message contains mymbox in the To: field.
 353   \"c\" indicates that the message contains mymbox in the Cc: field.
 354   \"b\" indicates that the message contains mymbox in the Bcc: field.
 355   \"n\" indicates that the message contains a Newsgroups: field.")
 356
 357 (defvar mh-scan-date-width 5
 358   "Number of columns consumed by the date field in `mh-scan-format'.
 359 This column will typically be of the form mm/dd.")
 360
 361 (defvar mh-scan-date-flag-width 1
 362   "Number of columns consumed to flag (in)valid dates in `mh-scan-format'.
 363 This column will have \" \" for valid and \"*\" for invalid or
 364 missing dates.")
 365
 366 (defvar mh-scan-from-mbox-width 17
 367   "Number of columns consumed with the \"From:\" line in `mh-scan-format'.
 368 This column will have a friendly name or e-mail address of the
 369 originator, or a \"To: address\" for outgoing e-mail messages.")
 370
 371 (defvar mh-scan-from-mbox-sep-width 2
 372   "Number of columns consumed by whitespace after from-mbox in `mh-scan-format'.
 373 This column will only ever have spaces in it.")
 374
 375 (defvar mh-scan-field-destination-offset
 376   (+ mh-scan-cmd-note-width)
 377   "The offset from the `mh-cmd-note' for the destination column.")
 378
 379 (defvar mh-scan-field-from-start-offset
 380   (+ mh-scan-cmd-note-width
 381      mh-scan-destination-width
 382      mh-scan-date-width
 383      mh-scan-date-flag-width)
 384   "The offset from the `mh-cmd-note' to find the start of \"From:\" address.")
 385
 386 (defvar mh-scan-field-from-end-offset
 387   (+ mh-scan-field-from-start-offset mh-scan-from-mbox-width)
 388   "The offset from the `mh-cmd-note' to find the end of \"From:\" address.")
 389
 390 (defvar mh-scan-field-subject-start-offset
 391   (+ mh-scan-cmd-note-width
 392      mh-scan-destination-width
 393      mh-scan-date-width
 394      mh-scan-date-flag-width
 395      mh-scan-from-mbox-width
 396      mh-scan-from-mbox-sep-width)
 397   "The offset from the `mh-cmd-note' to find the start of the subject.")
 398
 399 \f
 400
 401 ;;; Notation
 402
 403 ;; Alphabetical.
 404
 405 (defvar mh-note-blacklisted ?B
 406   "Messages that have been blacklisted are marked by this character.
 407 See also `mh-scan-blacklisted-msg-regexp'.")
 408
 409 (defvar mh-note-cur ?+
 410   "The current message (in MH, not in MH-E) is marked by this character.
 411 See also `mh-scan-cur-msg-number-regexp'.")
 412
 413 (defvar mh-note-copied ?C
 414   "Messages that have been copied are marked by this character.")
 415
 416 (defvar mh-note-deleted ?D
 417   "Messages that have been deleted are marked by this character.
 418 See also `mh-scan-deleted-msg-regexp'.")
 419
 420 (defvar mh-note-dist ?R
 421   "Messages that have been redistributed are marked by this character.")
 422
 423 (defvar mh-note-forw ?F
 424   "Messages that have been forwarded are marked by this character.")
 425
 426 (defvar mh-note-printed ?P
 427   "Messages that have been printed are marked by this character.")
 428
 429 (defvar mh-note-refiled ?^
 430   "Messages that have been refiled are marked by this character.
 431 See also `mh-scan-refiled-msg-regexp'.")
 432
 433 (defvar mh-note-repl ?-
 434   "Messages that have been replied to are marked by this character.")
 435
 436 (defvar mh-note-seq ?%
 437   "Messages in a user-defined sequence are marked by this character.
 438
 439 Messages in the \"search\" sequence are marked by this character as
 440 well.")
 441
 442 (defvar mh-note-whitelisted ?W
 443   "Messages that have been whitelisted are marked by this character.
 444 See also `mh-scan-whitelisted-msg-regexp'.")
 445
 446 \f
 447
 448 ;;; Utilities
 449
 450 ;;;###mh-autoload
 451 (defun mh-scan-msg-number-regexp ()
 452   "Return value of variable `mh-scan-msg-number-regexp'."
 453   mh-scan-msg-number-regexp)
 454
 455 ;;;###mh-autoload
 456 (defun mh-scan-msg-search-regexp ()
 457   "Return value of variable `mh-scan-msg-search-regexp'."
 458   mh-scan-msg-search-regexp)
 459
 460 ;;;###mh-autoload
 461 (defun mh-set-cmd-note (column)
 462   "Set `mh-cmd-note' to COLUMN.
 463 Note that columns in Emacs start with 0."
 464   (setq mh-cmd-note column))
 465
 466 ;;;###mh-autoload
 467 (defun mh-scan-format ()
 468   "Return the output format argument for the scan program."
 469   (if (equal mh-scan-format-file t)
 470       (list "-format" (if (mh-variant-p 'nmh 'gnu-mh)
 471                           (list (mh-update-scan-format
 472                                  mh-scan-format-nmh mh-cmd-note))
 473                         (list (mh-update-scan-format
 474                                mh-scan-format-mh mh-cmd-note))))
 475     (if (not (equal mh-scan-format-file nil))
 476         (list "-form" mh-scan-format-file))))
 477
 478 (defun mh-update-scan-format (fmt width)
 479   "Return a scan format with the (msg) width in the FMT replaced with WIDTH.
 480
 481 The message number width portion of the format is discovered
 482 using `mh-scan-msg-format-regexp'.  Its replacement is controlled
 483 with `mh-scan-msg-format-string'."
 484   (or (and
 485        (string-match mh-scan-msg-format-regexp fmt)
 486        (let ((begin (match-beginning 1))
 487              (end (match-end 1)))
 488          (concat (substring fmt 0 begin)
 489                  (format mh-scan-msg-format-string width)
 490                  (substring fmt end))))
 491       fmt))
 492
 493 ;;;###mh-autoload
 494 (defun mh-msg-num-width (folder)
 495   "Return the width of the largest message number in this FOLDER."
 496   (or mh-progs (mh-find-path))
 497   (let ((tmp-buffer (get-buffer-create mh-temp-buffer))
 498         (width 0))
 499     (with-current-buffer tmp-buffer
 500       (erase-buffer)
 501       (apply 'call-process
 502              (expand-file-name mh-scan-prog mh-progs) nil '(t nil) nil
 503              (list folder "last" "-format" "%(msg)"))
 504       (goto-char (point-min))
 505       (if (re-search-forward mh-scan-msg-number-regexp nil 0 1)
 506           (setq width (length (buffer-substring
 507                                (match-beginning 1) (match-end 1))))))
 508     width))
 509
 510 ;;;###mh-autoload
 511 (defun mh-msg-num-width-to-column (width)
 512   "Return the column for notations given message number WIDTH.
 513 Note that columns in Emacs start with 0.
 514
 515 If `mh-scan-format-file' is set to \"Use MH-E scan Format\" this
 516 means that either `mh-scan-format-mh' or `mh-scan-format-nmh' are
 517 in use.  This function therefore assumes that the first column is
 518 empty (to provide room for the cursor), the following WIDTH
 519 columns contain the message number, and the column for notations
 520 comes after that."
 521   (if (eq mh-scan-format-file t)
 522       (max (1+ width) 2)
 523     (error "%s %s" "Can't call `mh-msg-num-width-to-column' when"
 524            "`mh-scan-format-file' is not set to \"Use MH-E scan Format\"")))
 525
 526 (provide 'mh-scan)
 527
 528 ;; Local Variables:
 529 ;; indent-tabs-mode: nil
 530 ;; sentence-end-double-space: nil
 531 ;; End:
 532
 533 ;;; mh-scan.el ends here