root/src/viewer/ascii.c

/* [previous][next][first][last][top][bottom][index][help]  */

DEFINITIONS

This source file includes following definitions.
  1. mcview_wcwidth
  2. mcview_ismark
  3. mcview_is_non_spacing_mark
  4. mcview_is_spacing_mark
  5. mcview_isprint
  6. mcview_char_display
  7. mcview_get_next_char
  8. mcview_get_next_maybe_nroff_char
  9. mcview_next_combining_char_sequence
  10. mcview_display_line
  11. mcview_display_paragraph
  12. mcview_wrap_fixup
  13. mcview_display_text
  14. mcview_ascii_move_down
  15. mcview_ascii_move_up
  16. mcview_ascii_moveto_bol
  17. mcview_ascii_moveto_eol
  18. mcview_state_machine_init

   1 /*
   2    Internal file viewer for the Midnight Commander
   3    Function for plain view
   4 
   5    Copyright (C) 1994-2022
   6    Free Software Foundation, Inc.
   7 
   8    Written by:
   9    Miguel de Icaza, 1994, 1995, 1998
  10    Janne Kukonlehto, 1994, 1995
  11    Jakub Jelinek, 1995
  12    Joseph M. Hinkle, 1996
  13    Norbert Warmuth, 1997
  14    Pavel Machek, 1998
  15    Roland Illig <roland.illig@gmx.de>, 2004, 2005
  16    Slava Zanko <slavazanko@google.com>, 2009
  17    Andrew Borodin <aborodin@vmail.ru>, 2009-2022
  18    Ilia Maslakov <il.smind@gmail.com>, 2009
  19    Rewritten almost from scratch by:
  20    Egmont Koblinger <egmont@gmail.com>, 2014
  21 
  22    This file is part of the Midnight Commander.
  23 
  24    The Midnight Commander is free software: you can redistribute it
  25    and/or modify it under the terms of the GNU General Public License as
  26    published by the Free Software Foundation, either version 3 of the License,
  27    or (at your option) any later version.
  28 
  29    The Midnight Commander is distributed in the hope that it will be useful,
  30    but WITHOUT ANY WARRANTY; without even the implied warranty of
  31    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  32    GNU General Public License for more details.
  33 
  34    You should have received a copy of the GNU General Public License
  35    along with this program.  If not, see <http://www.gnu.org/licenses/>.
  36 
  37    ------------------------------------------------------------------------------------------------
  38 
  39    The viewer is implemented along the following design principles:
  40 
  41    Goals: Always display simple scripts, double wide (CJK), combining accents and spacing marks
  42    (often used e.g. in Devanagari) perfectly. Make the arrow keys always work correctly.
  43 
  44    Absolutely non-goal: RTL.
  45 
  46    Terminology:
  47 
  48    - A "paragraph" is the text between two adjacent newline characters. A "line" or "row" is a
  49    visual row on the screen. In wrap mode, the viewer formats a paragraph into one or more lines.
  50 
  51    - The Unicode glossary <http://www.unicode.org/glossary/> doesn't seem to have a notion of "base
  52    character followed by zero or more combining characters". The closest matches are "Combining
  53    Character Sequence" meaning a base character followed by one or more combining characters, or
  54    "Grapheme" which seems to exclude non-printable characters such as newline. In this file,
  55    "combining character sequence" (or any obvious abbreviation thereof) means a base character
  56    followed by zero or more (up to a current limit of 4) combining characters.
  57 
  58    ------------------------------------------------------------------------------------------------
  59 
  60    The parser-formatter is designed to be stateless across paragraphs. This is so that we can walk
  61    backwards without having to reparse the whole file (although we still need to reparse and
  62    reformat the whole paragraph, but it's a lot better). This principle needs to be changed if we
  63    ever get to address tickets 1849/2977, but then we can still store (for efficiency) the parser
  64    state at the beginning of the paragraph, and safely walk backwards if we don't cross an escape
  65    character.
  66 
  67    The parser-formatter, however, definitely needs to carry a state across lines. Currently this
  68    state contains:
  69 
  70    - The logical column (as if we didn't wrap). This is used for handling TAB characters after a
  71    wordwrap consistently with less.
  72 
  73    - Whether the last nroff character was bold or underlined. This is used for displaying the
  74    ambiguous _\b_ sequence consistently with less.
  75 
  76    - Whether the desired way of displaying a lonely combining accent or spacing mark is to place it
  77    over a dotted circle (we do this at the beginning of the paragraph of after a TAB), or to ignore
  78    the combining char and show replacement char for the spacing mark (we do this if e.g. too many
  79    of these were encountered and hence we don't glue them with their base character).
  80 
  81    - (This state needs to be expanded if e.g. we decide to print verbose replacement characters
  82    (e.g. "<U+0080>") and allow these to wrap around lines.)
  83 
  84    The state also contains the file offset, as it doesn't make sense to ever know the state without
  85    knowing the corresponding offset.
  86 
  87    The state depends on various settings (viewer width, encoding, nroff mode, charwrap or wordwrap
  88    mode (if we'll have that one day) etc.), needs to be recomputed if any of these changes.
  89 
  90    Walking forwards is usually relatively easy both in the file and on the screen. Walking
  91    backwards within a paragraph would only be possible in some special cases and even then it would
  92    be painful, so we always walk back to the beginning of the paragraph and reparse-reformat from
  93    there.
  94 
  95    (Walking back within a line in the file would have at least the following difficulties: handling
  96    the parser state; processing invalid UTF-8; processing invalid nroff (e.g. what is "_\bA\bA"?).
  97    Walking back on the display: we wouldn't know where to display the last line of a paragraph, or
  98    where to display a line if its following line starts with a wide (CJK or Tab) character. Long
  99    story short: just forget this approach.)
 100 
 101    Most important variables:
 102 
 103    - dpy_start: Both in unwrap and wrap modes this points to the beginning of the topmost displayed
 104    paragraph.
 105 
 106    - dpy_text_column: Only in unwrap mode, an additional horizontal scroll.
 107 
 108    - dpy_paragraph_skip_lines: Only in wrap mode, an additional vertical scroll (the number of
 109    lines that are scrolled off at the top from the topmost paragraph).
 110 
 111    - dpy_state_top: Only in wrap mode, the offset and parser-formatter state at the line where
 112    displaying the file begins is cached here.
 113 
 114    - dpy_wrap_dirty: If some parameter has changed that makes it necessary to reparse-redisplay the
 115    topmost paragraph.
 116 
 117    In wrap mode, the three variables "dpy_start", "dpy_paragraph_skip_lines" and "dpy_state_top"
 118    are kept consistent. Think of the first two as the ones describing the position, and the third
 119    as a cached value for better performance so that we don't need to wrap the invisible beginning
 120    of the topmost paragraph over and over again. The third value needs to be recomputed each time a
 121    parameter that influences parsing or displaying the file (e.g. width of screen, encoding, nroff
 122    mode) changes, this is signaled by "dpy_wrap_dirty" to force recomputing "dpy_state_top" (and
 123    clamp "dpy_paragraph_skip_lines" if necessary).
 124 
 125    ------------------------------------------------------------------------------------------------
 126 
 127    Help integration
 128 
 129    I'm planning to port the help viewer to this codebase.
 130 
 131    Splitting at sections would still happen in the help viewer. It would either copy a section, or
 132    set force_max and a similar force_min to limit displaying to one section only.
 133 
 134    Parsing the help format would go next to the nroff parser. The colors, alternate character set,
 135    and emitting the version number would go to the "state". (The version number would be
 136    implemented by emitting remaining characters of a buffer in the "state" one by one, without
 137    advancing in the file position.)
 138 
 139    The active link would be drawn similarly to the search highlight. Other than that, the viewer
 140    wouldn't care about links (except for their color). help.c would keep track of which one is
 141    highlighted, how to advance to the next/prev on an arrow, how the scroll offset needs to be
 142    adjusted when moving, etc.
 143 
 144    Add wrapping at word boundaries to where wrapping at char boundaries happens now.
 145  */
 146 
 147 #include <config.h>
 148 
 149 #include "lib/global.h"
 150 #include "lib/tty/tty.h"
 151 #include "lib/skin.h"
 152 #include "lib/util.h"           /* is_printable() */
 153 #ifdef HAVE_CHARSET
 154 #include "lib/charsets.h"
 155 #endif
 156 
 157 #include "src/setup.h"          /* option_tab_spacing */
 158 
 159 #include "internal.h"
 160 
 161 /*** global variables ****************************************************************************/
 162 
 163 /*** file scope macro definitions ****************************************************************/
 164 
 165 /* The Unicode standard recommends that lonely combining characters are printed over a dotted
 166  * circle. If the terminal is not UTF-8, this will be replaced by a dot anyway. */
 167 #define BASE_CHARACTER_FOR_LONELY_COMBINING 0x25CC      /* dotted circle */
 168 #define MAX_COMBINING_CHARS 4   /* both slang and ncurses support exactly 4 */
 169 
 170 /* I think anything other than space (e.g. arrows) just introduce visual clutter without actually
 171  * adding value. */
 172 #define PARTIAL_CJK_AT_LEFT_MARGIN  ' '
 173 #define PARTIAL_CJK_AT_RIGHT_MARGIN ' '
 174 
 175 /*
 176  * Wrap mode: This is for safety so that jumping to the end of file (which already includes
 177  * scrolling back by a page) and then walking backwards is reasonably fast, even if the file is
 178  * extremely large and consists of maybe full zeros or something like that. If there's no newline
 179  * found within this limit, just start displaying from there and see what happens. We might get
 180  * some displaying parameteres (most importantly the columns) incorrect, but at least will show the
 181  * file without spinning the CPU for ages. When scrolling back to that point, the user might see a
 182  * garbled first line (even starting with an invalid partial UTF-8), but then walking back by yet
 183  * another line should fix it.
 184  *
 185  * Unwrap mode: This is not used, we wouldn't be able to do anything reasonable without walking
 186  * back a whole paragraph (well, view->data_area.height paragraphs actually).
 187  */
 188 #define MAX_BACKWARDS_WALK_IN_PARAGRAPH (100 * 1000)
 189 
 190 /*** file scope type declarations ****************************************************************/
 191 
 192 /*** file scope variables ************************************************************************/
 193 
 194 /* --------------------------------------------------------------------------------------------- */
 195 /*** file scope functions ************************************************************************/
 196 /* --------------------------------------------------------------------------------------------- */
 197 
 198 /* TODO: These methods shouldn't be necessary, see ticket 3257 */
 199 
 200 static int
 201 mcview_wcwidth (const WView * view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 202 {
 203 #ifdef HAVE_CHARSET
 204     if (view->utf8)
 205     {
 206         if (g_unichar_iswide (c))
 207             return 2;
 208         if (g_unichar_iszerowidth (c))
 209             return 0;
 210     }
 211 #else
 212     (void) view;
 213     (void) c;
 214 #endif /* HAVE_CHARSET */
 215     return 1;
 216 }
 217 
 218 /* --------------------------------------------------------------------------------------------- */
 219 
 220 static gboolean
 221 mcview_ismark (const WView * view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 222 {
 223 #ifdef HAVE_CHARSET
 224     if (view->utf8)
 225         return g_unichar_ismark (c);
 226 #else
 227     (void) view;
 228     (void) c;
 229 #endif /* HAVE_CHARSET */
 230     return FALSE;
 231 }
 232 
 233 /* --------------------------------------------------------------------------------------------- */
 234 
 235 /* actually is_non_spacing_mark_or_enclosing_mark */
 236 static gboolean
 237 mcview_is_non_spacing_mark (const WView * view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 238 {
 239 #ifdef HAVE_CHARSET
 240     if (view->utf8)
 241     {
 242         GUnicodeType type;
 243 
 244         type = g_unichar_type (c);
 245 
 246         return type == G_UNICODE_NON_SPACING_MARK || type == G_UNICODE_ENCLOSING_MARK;
 247     }
 248 #else
 249     (void) view;
 250     (void) c;
 251 #endif /* HAVE_CHARSET */
 252     return FALSE;
 253 }
 254 
 255 /* --------------------------------------------------------------------------------------------- */
 256 
 257 #if 0
 258 static gboolean
 259 mcview_is_spacing_mark (const WView * view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 260 {
 261 #ifdef HAVE_CHARSET
 262     if (view->utf8)
 263         return g_unichar_type (c) == G_UNICODE_SPACING_MARK;
 264 #else
 265     (void) view;
 266     (void) c;
 267 #endif /* HAVE_CHARSET */
 268     return FALSE;
 269 }
 270 #endif /* 0 */
 271 
 272 /* --------------------------------------------------------------------------------------------- */
 273 
 274 static gboolean
 275 mcview_isprint (const WView * view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 276 {
 277 #ifdef HAVE_CHARSET
 278     if (!view->utf8)
 279         c = convert_from_8bit_to_utf_c ((unsigned char) c, view->converter);
 280     return g_unichar_isprint (c);
 281 #else
 282     (void) view;
 283     /* TODO this is very-very buggy by design: ticket 3257 comments 0-1 */
 284     return is_printable (c);
 285 #endif /* HAVE_CHARSET */
 286 }
 287 
 288 /* --------------------------------------------------------------------------------------------- */
 289 
 290 static int
 291 mcview_char_display (const WView * view, int c, char *s)
     /* [previous][next][first][last][top][bottom][index][help]  */
 292 {
 293 #ifdef HAVE_CHARSET
 294     if (mc_global.utf8_display)
 295     {
 296         if (!view->utf8)
 297             c = convert_from_8bit_to_utf_c ((unsigned char) c, view->converter);
 298         if (!g_unichar_isprint (c))
 299             c = '.';
 300         return g_unichar_to_utf8 (c, s);
 301     }
 302     if (view->utf8)
 303     {
 304         if (g_unichar_iswide (c))
 305         {
 306             s[0] = s[1] = '.';
 307             return 2;
 308         }
 309         if (g_unichar_iszerowidth (c))
 310             return 0;
 311         /* TODO the is_printable check below will be broken for this */
 312         c = convert_from_utf_to_current_c (c, view->converter);
 313     }
 314     else
 315     {
 316         /* TODO the is_printable check below will be broken for this */
 317         c = convert_to_display_c (c);
 318     }
 319 #else
 320     (void) view;
 321 #endif /* HAVE_CHARSET */
 322     /* TODO this is very-very buggy by design: ticket 3257 comments 0-1 */
 323     if (!is_printable (c))
 324         c = '.';
 325     *s = c;
 326     return 1;
 327 }
 328 
 329 /* --------------------------------------------------------------------------------------------- */
 330 
 331 /**
 332  * Just for convenience, a common interface in front of mcview_get_utf and mcview_get_byte, so that
 333  * the caller doesn't have to care about utf8 vs 8-bit modes.
 334  *
 335  * Normally: stores c, updates state, returns TRUE.
 336  * At EOF: state is unchanged, c is undefined, returns FALSE.
 337  *
 338  * Just as with mcview_get_utf(), invalid UTF-8 is reported using negative integers.
 339  *
 340  * Also, temporary hack: handle force_max here.
 341  * TODO: move it to lower layers (datasource.c)?
 342  */
 343 static gboolean
 344 mcview_get_next_char (WView * view, mcview_state_machine_t * state, int *c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 345 {
 346     /* Pretend EOF if we reached force_max */
 347     if (view->force_max >= 0 && state->offset >= view->force_max)
 348         return FALSE;
 349 
 350 #ifdef HAVE_CHARSET
 351     if (view->utf8)
 352     {
 353         int char_length = 0;
 354 
 355         if (!mcview_get_utf (view, state->offset, c, &char_length))
 356             return FALSE;
 357         /* Pretend EOF if we crossed force_max */
 358         if (view->force_max >= 0 && state->offset + char_length > view->force_max)
 359             return FALSE;
 360 
 361         state->offset += char_length;
 362         return TRUE;
 363     }
 364 #endif /* HAVE_CHARSET */
 365     if (!mcview_get_byte (view, state->offset, c))
 366         return FALSE;
 367     state->offset++;
 368     return TRUE;
 369 }
 370 
 371 /* --------------------------------------------------------------------------------------------- */
 372 /**
 373  * This function parses the next nroff character and gives it to you along with its desired color,
 374  * so you never have to care about nroff again.
 375  *
 376  * The nroff mode does the backspace trick for every single character (Unicode codepoint). At least
 377  * that's what the GNU groff 1.22 package produces, and that's what less 458 expects. For
 378  * double-wide characters (CJK), still only a single backspace is emitted. For combining accents
 379  * and such, the print-backspace-print step is repeated for the base character and then for each
 380  * accent separately.
 381  *
 382  * So, the right place for this layer is after the bytes are interpreted in UTF-8, but before
 383  * joining a base character with its combining accents.
 384  *
 385  * Normally: stores c and color, updates state, returns TRUE.
 386  * At EOF: state is unchanged, c and color are undefined, returns FALSE.
 387  *
 388  * color can be null if the caller doesn't care.
 389  */
 390 static gboolean
 391 mcview_get_next_maybe_nroff_char (WView * view, mcview_state_machine_t * state, int *c, int *color)
     /* [previous][next][first][last][top][bottom][index][help]  */
 392 {
 393     mcview_state_machine_t state_after_nroff;
 394     int c2, c3;
 395 
 396     if (color != NULL)
 397         *color = VIEW_NORMAL_COLOR;
 398 
 399     if (!view->mode_flags.nroff)
 400         return mcview_get_next_char (view, state, c);
 401 
 402     if (!mcview_get_next_char (view, state, c))
 403         return FALSE;
 404     /* Don't allow nroff formatting around CR, LF, TAB or other special chars */
 405     if (!mcview_isprint (view, *c))
 406         return TRUE;
 407 
 408     state_after_nroff = *state;
 409 
 410     if (!mcview_get_next_char (view, &state_after_nroff, &c2))
 411         return TRUE;
 412     if (c2 != '\b')
 413         return TRUE;
 414 
 415     if (!mcview_get_next_char (view, &state_after_nroff, &c3))
 416         return TRUE;
 417     if (!mcview_isprint (view, c3))
 418         return TRUE;
 419 
 420     if (*c == '_' && c3 == '_')
 421     {
 422         *state = state_after_nroff;
 423         if (color != NULL)
 424             *color =
 425                 state->nroff_underscore_is_underlined ? VIEW_UNDERLINED_COLOR : VIEW_BOLD_COLOR;
 426     }
 427     else if (*c == c3)
 428     {
 429         *state = state_after_nroff;
 430         state->nroff_underscore_is_underlined = FALSE;
 431         if (color != NULL)
 432             *color = VIEW_BOLD_COLOR;
 433     }
 434     else if (*c == '_')
 435     {
 436         *c = c3;
 437         *state = state_after_nroff;
 438         state->nroff_underscore_is_underlined = TRUE;
 439         if (color != NULL)
 440             *color = VIEW_UNDERLINED_COLOR;
 441     }
 442 
 443     return TRUE;
 444 }
 445 
 446 /* --------------------------------------------------------------------------------------------- */
 447 /**
 448  * Get one base character, along with its combining or spacing mark characters.
 449  *
 450  * (A spacing mark is a character that extends the base character's width 1 into a combined
 451  * character of width 2, yet these two character cells should not be separated. E.g. Devanagari
 452  * <U+0939><U+094B>.)
 453  *
 454  * This method exists mainly for two reasons. One is to be able to tell if we fit on the current
 455  * line or need to wrap to the next one. The other is that both slang and ncurses seem to require
 456  * that the character and its combining marks are printed in a single call (or is it just a
 457  * limitation of mc's wrapper to them?).
 458  *
 459  * For convenience, this method takes care of converting CR or CR+LF into LF.
 460  * TODO this should probably happen later, when displaying the file?
 461  *
 462  * Normally: stores cs and color, updates state, returns >= 1 (entries in cs).
 463  * At EOF: state is unchanged, cs and color are undefined, returns 0.
 464  *
 465  * @param view ...
 466  * @param state the parser-formatter state machine's state, updated
 467  * @param cs store the characters here
 468  * @param clen the room available in cs (that is, at most clen-1 combining marks are allowed), must
 469  *   be at least 2
 470  * @param color if non-NULL, store the color here, taken from the first codepoint's color
 471  * @return the number of entries placed in cs, or 0 on EOF
 472  */
 473 static int
 474 mcview_next_combining_char_sequence (WView * view, mcview_state_machine_t * state, int *cs,
     /* [previous][next][first][last][top][bottom][index][help]  */
 475                                      int clen, int *color)
 476 {
 477     int i = 1;
 478 
 479     if (!mcview_get_next_maybe_nroff_char (view, state, cs, color))
 480         return 0;
 481 
 482     /* Process \r and \r\n newlines. */
 483     if (cs[0] == '\r')
 484     {
 485         int cnext;
 486 
 487         mcview_state_machine_t state_after_crlf = *state;
 488         if (mcview_get_next_maybe_nroff_char (view, &state_after_crlf, &cnext, NULL)
 489             && cnext == '\n')
 490             *state = state_after_crlf;
 491         cs[0] = '\n';
 492         return 1;
 493     }
 494 
 495     /* We don't want combining over non-printable characters. This includes '\n' and '\t' too. */
 496     if (!mcview_isprint (view, cs[0]))
 497         return 1;
 498 
 499     if (mcview_ismark (view, cs[0]))
 500     {
 501         if (!state->print_lonely_combining)
 502         {
 503             /* First character is combining. Either just return it, ... */
 504             return 1;
 505         }
 506         else
 507         {
 508             /* or place this (and subsequent combining ones) over a dotted circle. */
 509             cs[1] = cs[0];
 510             cs[0] = BASE_CHARACTER_FOR_LONELY_COMBINING;
 511             i = 2;
 512         }
 513     }
 514 
 515     if (mcview_wcwidth (view, cs[0]) == 2)
 516     {
 517         /* Don't allow combining or spacing mark for wide characters, is this okay? */
 518         return 1;
 519     }
 520 
 521     /* Look for more combining chars. Either at most clen-1 zero-width combining chars,
 522      * or at most 1 spacing mark. Is this logic correct? */
 523     for (; i < clen; i++)
 524     {
 525         mcview_state_machine_t state_after_combining;
 526 
 527         state_after_combining = *state;
 528         if (!mcview_get_next_maybe_nroff_char (view, &state_after_combining, &cs[i], NULL))
 529             return i;
 530         if (!mcview_ismark (view, cs[i]) || !mcview_isprint (view, cs[i]))
 531             return i;
 532         if (g_unichar_type (cs[i]) == G_UNICODE_SPACING_MARK)
 533         {
 534             /* Only allow as the first combining char. Stop processing in either case. */
 535             if (i == 1)
 536             {
 537                 *state = state_after_combining;
 538                 i++;
 539             }
 540             return i;
 541         }
 542         *state = state_after_combining;
 543     }
 544     return i;
 545 }
 546 
 547 /* --------------------------------------------------------------------------------------------- */
 548 /**
 549  * Parse, format and possibly display one visual line of text.
 550  *
 551  * Formatting starts at the given "state" (which encodes the file offset and parser and formatter's
 552  * internal state). In unwrap mode, this should point to the beginning of the paragraph with the
 553  * default state, the additional horizontal scrolling is added here. In wrap mode, this should
 554  * point to the beginning of the line, with the proper state at that point.
 555  *
 556  * In wrap mode, if a line ends in a newline, it is consumed, even if it's exactly at the right
 557  * edge. In unwrap mode, the whole remaining line, including the newline is consumed. Displaying
 558  * the next line should start at "state"'s new value, or if we displayed the bottom line then
 559  * state->offset tells the file offset to be shown in the top bar.
 560  *
 561  * If "row" is offscreen, don't actually display the line but still update "state" and return the
 562  * proper value. This is used by mcview_wrap_move_down to advance in the file.
 563  *
 564  * @param view ...
 565  * @param state the parser-formatter state machine's state, updated
 566  * @param row print to this row
 567  * @param paragraph_ended store TRUE if paragraph ended by newline or EOF, FALSE if wraps to next
 568  *   line
 569  * @param linewidth store the width of the line here
 570  * @return the number of rows, that is, 0 if we were already at EOF, otherwise 1
 571  */
 572 static int
 573 mcview_display_line (WView * view, mcview_state_machine_t * state, int row,
     /* [previous][next][first][last][top][bottom][index][help]  */
 574                      gboolean * paragraph_ended, off_t * linewidth)
 575 {
 576     const WRect *r = &view->data_area;
 577     off_t dpy_text_column = view->mode_flags.wrap ? 0 : view->dpy_text_column;
 578     int col = 0;
 579     int cs[1 + MAX_COMBINING_CHARS];
 580     char str[(1 + MAX_COMBINING_CHARS) * UTF8_CHAR_LEN + 1];
 581     int i, j;
 582 
 583     if (paragraph_ended != NULL)
 584         *paragraph_ended = TRUE;
 585 
 586     if (!view->mode_flags.wrap && (row < 0 || row >= r->lines) && linewidth == NULL)
 587     {
 588         /* Optimization: Fast forward to the end of the line, rather than carefully
 589          * parsing and then not actually displaying it. */
 590         off_t eol;
 591         int retval;
 592 
 593         eol = mcview_eol (view, state->offset);
 594         retval = (eol > state->offset) ? 1 : 0;
 595 
 596         mcview_state_machine_init (state, eol);
 597         return retval;
 598     }
 599 
 600     while (TRUE)
 601     {
 602         int charwidth = 0;
 603         mcview_state_machine_t state_saved;
 604         int n;
 605         int color;
 606 
 607         state_saved = *state;
 608         n = mcview_next_combining_char_sequence (view, state, cs, 1 + MAX_COMBINING_CHARS, &color);
 609         if (n == 0)
 610         {
 611             if (linewidth != NULL)
 612                 *linewidth = col;
 613             return (col > 0) ? 1 : 0;
 614         }
 615 
 616         if (view->search_start <= state->offset && state->offset < view->search_end)
 617             color = VIEW_SELECTED_COLOR;
 618 
 619         if (cs[0] == '\n')
 620         {
 621             /* New line: reset all formatting state for the next paragraph. */
 622             mcview_state_machine_init (state, state->offset);
 623             if (linewidth != NULL)
 624                 *linewidth = col;
 625             return 1;
 626         }
 627 
 628         if (mcview_is_non_spacing_mark (view, cs[0]))
 629         {
 630             /* Lonely combining character. Probably leftover after too many combining chars. Just ignore. */
 631             continue;
 632         }
 633 
 634         /* Nonprintable, or lonely spacing mark */
 635         if ((!mcview_isprint (view, cs[0]) || mcview_ismark (view, cs[0])) && cs[0] != '\t')
 636             cs[0] = '.';
 637 
 638         for (i = 0; i < n; i++)
 639             charwidth += mcview_wcwidth (view, cs[i]);
 640 
 641         /* Adjust the width for TAB. It's handled below along with the normal characters,
 642          * so that it's wrapped consistently with them, and is painted with the proper
 643          * attributes (although currently it can't have a special color). */
 644         if (cs[0] == '\t')
 645         {
 646             charwidth = option_tab_spacing - state->unwrapped_column % option_tab_spacing;
 647             state->print_lonely_combining = TRUE;
 648         }
 649         else
 650             state->print_lonely_combining = FALSE;
 651 
 652         /* In wrap mode only: We're done with this row if the character sequence wouldn't fit.
 653          * Except if at the first column, because then it wouldn't fit in the next row either.
 654          * In this extreme case let the unwrapped code below do its best to display it. */
 655         if (view->mode_flags.wrap && (off_t) col + charwidth > dpy_text_column + (off_t) r->cols
 656             && col > 0)
 657         {
 658             *state = state_saved;
 659             if (paragraph_ended != NULL)
 660                 *paragraph_ended = FALSE;
 661             if (linewidth != NULL)
 662                 *linewidth = col;
 663             return 1;
 664         }
 665 
 666         /* Display, unless outside of the viewport. */
 667         if (row >= 0 && row < r->lines)
 668         {
 669             if ((off_t) col >= dpy_text_column &&
 670                 (off_t) col + charwidth <= dpy_text_column + (off_t) r->cols)
 671             {
 672                 /* The combining character sequence fits entirely in the viewport. Print it. */
 673                 tty_setcolor (color);
 674                 widget_gotoyx (view, r->y + row, r->x + ((off_t) col - dpy_text_column));
 675                 if (cs[0] == '\t')
 676                 {
 677                     for (i = 0; i < charwidth; i++)
 678                         tty_print_char (' ');
 679                 }
 680                 else
 681                 {
 682                     j = 0;
 683                     for (i = 0; i < n; i++)
 684                         j += mcview_char_display (view, cs[i], str + j);
 685                     str[j] = '\0';
 686                     /* This is probably a bug in our tty layer, but tty_print_string
 687                      * normalizes the string, whereas tty_printf doesn't. Don't normalize,
 688                      * since we handle combining characters ourselves correctly, it's
 689                      * better if they are copy-pasted correctly. Ticket 3255. */
 690                     tty_printf ("%s", str);
 691                 }
 692             }
 693             else if ((off_t) col < dpy_text_column && (off_t) col + charwidth > dpy_text_column)
 694             {
 695                 /* The combining character sequence would cross the left edge of the viewport.
 696                  * This cannot happen with wrap mode. Print replacement character(s),
 697                  * or spaces with the correct attributes for partial Tabs. */
 698                 tty_setcolor (color);
 699                 for (i = dpy_text_column;
 700                      i < (off_t) col + charwidth && i < dpy_text_column + (off_t) r->cols; i++)
 701                 {
 702                     widget_gotoyx (view, r->y + row, r->x + (i - dpy_text_column));
 703                     tty_print_anychar ((cs[0] == '\t') ? ' ' : PARTIAL_CJK_AT_LEFT_MARGIN);
 704                 }
 705             }
 706             else if ((off_t) col < dpy_text_column + (off_t) r->cols &&
 707                      (off_t) col + charwidth > dpy_text_column + (off_t) r->cols)
 708             {
 709                 /* The combining character sequence would cross the right edge of the viewport
 710                  * and we're not wrapping. Print replacement character(s),
 711                  * or spaces with the correct attributes for partial Tabs. */
 712                 tty_setcolor (color);
 713                 for (i = col; i < dpy_text_column + (off_t) r->cols; i++)
 714                 {
 715                     widget_gotoyx (view, r->y + row, r->x + (i - dpy_text_column));
 716                     tty_print_anychar ((cs[0] == '\t') ? ' ' : PARTIAL_CJK_AT_RIGHT_MARGIN);
 717                 }
 718             }
 719         }
 720 
 721         col += charwidth;
 722         state->unwrapped_column += charwidth;
 723 
 724         if (!view->mode_flags.wrap && (off_t) col >= dpy_text_column + (off_t) r->cols
 725             && linewidth == NULL)
 726         {
 727             /* Optimization: Fast forward to the end of the line, rather than carefully
 728              * parsing and then not actually displaying it. */
 729             off_t eol;
 730 
 731             eol = mcview_eol (view, state->offset);
 732             mcview_state_machine_init (state, eol);
 733             return 1;
 734         }
 735     }
 736 }
 737 
 738 /* --------------------------------------------------------------------------------------------- */
 739 /**
 740  * Parse, format and possibly display one paragraph (perhaps not from the beginning).
 741  *
 742  * Formatting starts at the given "state" (which encodes the file offset and parser and formatter's
 743  * internal state). In unwrap mode, this should point to the beginning of the paragraph with the
 744  * default state, the additional horizontal scrolling is added here. In wrap mode, this may point
 745  * to the beginning of the line within a paragraph (to display the partial paragraph at the top),
 746  * with the proper state at that point.
 747  *
 748  * Displaying the next paragraph should start at "state"'s new value, or if we displayed the bottom
 749  * line then state->offset tells the file offset to be shown in the top bar.
 750  *
 751  * If "row" is negative, don't display the first abs(row) lines and display the rest from the top.
 752  * This was a nice idea but it's now unused :)
 753  *
 754  * If "row" is too large, don't display the paragraph at all but still return the number of lines.
 755  * This is used when moving upwards.
 756  *
 757  * @param view ...
 758  * @param state the parser-formatter state machine's state, updated
 759  * @param row print starting at this row
 760  * @return the number of rows the paragraphs is wrapped to, that is, 0 if we were already at EOF,
 761  *   otherwise 1 in unwrap mode, >= 1 in wrap mode. We stop when reaching the bottom of the
 762  *   viewport, it's not counted how many more lines the paragraph would occupy
 763  */
 764 static int
 765 mcview_display_paragraph (WView * view, mcview_state_machine_t * state, int row)
     /* [previous][next][first][last][top][bottom][index][help]  */
 766 {
 767     int lines = 0;
 768 
 769     while (TRUE)
 770     {
 771         gboolean paragraph_ended;
 772 
 773         lines += mcview_display_line (view, state, row, &paragraph_ended, NULL);
 774         if (paragraph_ended)
 775             return lines;
 776 
 777         if (row < view->data_area.lines)
 778         {
 779             row++;
 780             /* stop if bottom of screen reached */
 781             if (row >= view->data_area.lines)
 782                 return lines;
 783         }
 784     }
 785 }
 786 
 787 /* --------------------------------------------------------------------------------------------- */
 788 /**
 789  * Recompute dpy_state_top from dpy_start and dpy_paragraph_skip_lines. Clamp
 790  * dpy_paragraph_skip_lines if necessary.
 791  *
 792  * This method should be called in wrap mode after changing one of the parsing or formatting
 793  * properties (e.g. window width, encoding, nroff), or when switching to wrap mode from unwrap or
 794  * hex.
 795  *
 796  * If we stayed within the same paragraph then try to keep the vertical offset within that
 797  * paragraph as well. It might happen though that the paragraph became shorter than our desired
 798  * vertical position, in that case move to its last row.
 799  */
 800 static void
 801 mcview_wrap_fixup (WView * view)
     /* [previous][next][first][last][top][bottom][index][help]  */
 802 {
 803     int lines = view->dpy_paragraph_skip_lines;
 804 
 805     if (!view->dpy_wrap_dirty)
 806         return;
 807     view->dpy_wrap_dirty = FALSE;
 808 
 809     view->dpy_paragraph_skip_lines = 0;
 810     mcview_state_machine_init (&view->dpy_state_top, view->dpy_start);
 811 
 812     while (lines-- != 0)
 813     {
 814         mcview_state_machine_t state_prev;
 815         gboolean paragraph_ended;
 816 
 817         state_prev = view->dpy_state_top;
 818         if (mcview_display_line (view, &view->dpy_state_top, -1, &paragraph_ended, NULL) == 0)
 819             break;
 820         if (paragraph_ended)
 821         {
 822             view->dpy_state_top = state_prev;
 823             break;
 824         }
 825         view->dpy_paragraph_skip_lines++;
 826     }
 827 }
 828 
 829 /* --------------------------------------------------------------------------------------------- */
 830 /*** public functions ****************************************************************************/
 831 /* --------------------------------------------------------------------------------------------- */
 832 
 833 /**
 834  * In both wrap and unwrap modes, dpy_start points to the beginning of the paragraph.
 835  *
 836  * In unwrap mode, start displaying from this position, probably applying an additional horizontal
 837  * scroll.
 838  *
 839  * In wrap mode, an additional dpy_paragraph_skip_lines lines are skipped from the top of this
 840  * paragraph. dpy_state_top contains the position and parser-formatter state corresponding to the
 841  * top left corner so we can just start rendering from here. Unless dpy_wrap_dirty is set in which
 842  * case dpy_state_top is invalid and we need to recompute first.
 843  */
 844 void
 845 mcview_display_text (WView * view)
     /* [previous][next][first][last][top][bottom][index][help]  */
 846 {
 847     const WRect *r = &view->data_area;
 848     int row;
 849     mcview_state_machine_t state;
 850     gboolean again;
 851 
 852     do
 853     {
 854         int n;
 855 
 856         again = FALSE;
 857 
 858         mcview_display_clean (view);
 859         mcview_display_ruler (view);
 860 
 861         if (!view->mode_flags.wrap)
 862             mcview_state_machine_init (&state, view->dpy_start);
 863         else
 864         {
 865             mcview_wrap_fixup (view);
 866             state = view->dpy_state_top;
 867         }
 868 
 869         for (row = 0; row < r->lines; row += n)
 870         {
 871             n = mcview_display_paragraph (view, &state, row);
 872             if (n == 0)
 873             {
 874                 /* In the rare case that displaying didn't start at the beginning
 875                  * of the file, yet there are some empty lines at the bottom,
 876                  * scroll the file and display again. This happens when e.g. the
 877                  * window is made bigger, or the file becomes shorter due to
 878                  * charset change or enabling nroff. */
 879                 if ((view->mode_flags.wrap ? view->dpy_state_top.offset : view->dpy_start) > 0)
 880                 {
 881                     mcview_ascii_move_up (view, r->lines - row);
 882                     again = TRUE;
 883                 }
 884                 break;
 885             }
 886         }
 887     }
 888     while (again);
 889 
 890     view->dpy_end = state.offset;
 891     view->dpy_state_bottom = state;
 892 
 893     tty_setcolor (VIEW_NORMAL_COLOR);
 894     if (mcview_show_eof != NULL && mcview_show_eof[0] != '\0')
 895         while (row < r->lines)
 896         {
 897             widget_gotoyx (view, r->y + row, r->x);
 898             /* TODO: should make it no wider than the viewport */
 899             tty_print_string (mcview_show_eof);
 900             row++;
 901         }
 902 }
 903 
 904 /* --------------------------------------------------------------------------------------------- */
 905 /**
 906  * Move down.
 907  *
 908  * It's very simple. Just invisibly format the next "lines" lines, carefully carrying the formatter
 909  * state in wrap mode. But before each step we need to check if we've already hit the end of the
 910  * file, in that case we can no longer move. This is done by walking from dpy_state_bottom.
 911  *
 912  * Note that this relies on mcview_display_text() setting dpy_state_bottom to its correct value
 913  * upon rendering the screen contents. So don't call this function from other functions (e.g. at
 914  * the bottom of mcview_ascii_move_up()) which invalidate this value.
 915  */
 916 void
 917 mcview_ascii_move_down (WView * view, off_t lines)
     /* [previous][next][first][last][top][bottom][index][help]  */
 918 {
 919     while (lines-- != 0)
 920     {
 921         gboolean paragraph_ended;
 922 
 923         /* See if there's still data below the bottom line, by imaginarily displaying one
 924          * more line. This takes care of reading more data into growbuf, if required.
 925          * If the end position didn't advance, we're at EOF and hence bail out. */
 926         if (mcview_display_line (view, &view->dpy_state_bottom, -1, &paragraph_ended, NULL) == 0)
 927             break;
 928 
 929         /* Okay, there's enough data. Move by 1 row at the top, too. No need to check for
 930          * EOF, that can't happen. */
 931         if (!view->mode_flags.wrap)
 932         {
 933             view->dpy_start = mcview_eol (view, view->dpy_start);
 934             view->dpy_paragraph_skip_lines = 0;
 935             view->dpy_wrap_dirty = TRUE;
 936         }
 937         else
 938         {
 939             mcview_display_line (view, &view->dpy_state_top, -1, &paragraph_ended, NULL);
 940             if (!paragraph_ended)
 941                 view->dpy_paragraph_skip_lines++;
 942             else
 943             {
 944                 view->dpy_start = view->dpy_state_top.offset;
 945                 view->dpy_paragraph_skip_lines = 0;
 946             }
 947         }
 948     }
 949 }
 950 
 951 /* --------------------------------------------------------------------------------------------- */
 952 /**
 953  * Move up.
 954  *
 955  * Unwrap mode: Piece of cake. Wrap mode: If we'd walk back more than the current line offset
 956  * within the paragraph, we need to jump back to the previous paragraph and compute its height to
 957  * see if we start from that paragraph, and repeat this if necessary. Once we're within the desired
 958  * paragraph, we still need to format it from its beginning to know the state.
 959  *
 960  * See the top of this file for comments about MAX_BACKWARDS_WALK_IN_PARAGRAPH.
 961  *
 962  * force_max is a nice protection against the rare extreme case that the file underneath us
 963  * changes, we don't want to endlessly consume a file of maybe full of zeros upon moving upwards.
 964  */
 965 void
 966 mcview_ascii_move_up (WView * view, off_t lines)
     /* [previous][next][first][last][top][bottom][index][help]  */
 967 {
 968     if (!view->mode_flags.wrap)
 969     {
 970         while (lines-- != 0)
 971             view->dpy_start = mcview_bol (view, view->dpy_start - 1, 0);
 972         view->dpy_paragraph_skip_lines = 0;
 973         view->dpy_wrap_dirty = TRUE;
 974     }
 975     else
 976     {
 977         int i;
 978 
 979         while (lines > view->dpy_paragraph_skip_lines)
 980         {
 981             /* We need to go back to the previous paragraph. */
 982             if (view->dpy_start == 0)
 983             {
 984                 /* Oops, we're already in the first paragraph. */
 985                 view->dpy_paragraph_skip_lines = 0;
 986                 mcview_state_machine_init (&view->dpy_state_top, 0);
 987                 return;
 988             }
 989             lines -= view->dpy_paragraph_skip_lines;
 990             view->force_max = view->dpy_start;
 991             view->dpy_start =
 992                 mcview_bol (view, view->dpy_start - 1,
 993                             view->dpy_start - MAX_BACKWARDS_WALK_IN_PARAGRAPH);
 994             mcview_state_machine_init (&view->dpy_state_top, view->dpy_start);
 995             /* This is a tricky way of denoting that we're at the end of the paragraph.
 996              * Normally we'd jump to the next paragraph and reset paragraph_skip_lines. But for
 997              * walking backwards this is exactly what we need. */
 998             view->dpy_paragraph_skip_lines =
 999                 mcview_display_paragraph (view, &view->dpy_state_top, view->data_area.lines);
1000             view->force_max = -1;
1001         }
1002 
1003         /* Okay, we have have dpy_start pointing to the desired paragraph, and we still need to
1004          * walk back "lines" lines from the current "dpy_paragraph_skip_lines" offset. We can't do
1005          * that, so walk from the beginning of the paragraph. */
1006         mcview_state_machine_init (&view->dpy_state_top, view->dpy_start);
1007         view->dpy_paragraph_skip_lines -= lines;
1008         for (i = 0; i < view->dpy_paragraph_skip_lines; i++)
1009             mcview_display_line (view, &view->dpy_state_top, -1, NULL, NULL);
1010     }
1011 }
1012 
1013 /* --------------------------------------------------------------------------------------------- */
1014 
1015 void
1016 mcview_ascii_moveto_bol (WView * view)
     /* [previous][next][first][last][top][bottom][index][help]  */
1017 {
1018     if (!view->mode_flags.wrap)
1019         view->dpy_text_column = 0;
1020 }
1021 
1022 /* --------------------------------------------------------------------------------------------- */
1023 
1024 void
1025 mcview_ascii_moveto_eol (WView * view)
     /* [previous][next][first][last][top][bottom][index][help]  */
1026 {
1027     if (!view->mode_flags.wrap)
1028     {
1029         mcview_state_machine_t state;
1030         off_t linewidth;
1031 
1032         /* Get the width of the topmost paragraph. */
1033         mcview_state_machine_init (&state, view->dpy_start);
1034         mcview_display_line (view, &state, -1, NULL, &linewidth);
1035         view->dpy_text_column = DOZ (linewidth, (off_t) view->data_area.cols);
1036     }
1037 }
1038 
1039 /* --------------------------------------------------------------------------------------------- */
1040 
1041 void
1042 mcview_state_machine_init (mcview_state_machine_t * state, off_t offset)
     /* [previous][next][first][last][top][bottom][index][help]  */
1043 {
1044     memset (state, 0, sizeof (*state));
1045     state->offset = offset;
1046     state->print_lonely_combining = TRUE;
1047 }
1048 
1049 /* --------------------------------------------------------------------------------------------- */

/* [previous][next][first][last][top][bottom][index][help]  */