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) 1994-2024
   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 parameters (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 /*** forward declarations (file scope functions) *************************************************/
 193 
 194 /*** file scope variables ************************************************************************/
 195 
 196 /* --------------------------------------------------------------------------------------------- */
 197 /*** file scope functions ************************************************************************/
 198 /* --------------------------------------------------------------------------------------------- */
 199 
 200 /* TODO: These methods shouldn't be necessary, see ticket 3257 */
 201 
 202 static int
 203 mcview_wcwidth (const WView *view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 204 {
 205 #ifdef HAVE_CHARSET
 206     if (view->utf8)
 207     {
 208         if (g_unichar_iswide (c))
 209             return 2;
 210         if (g_unichar_iszerowidth (c))
 211             return 0;
 212     }
 213 #else
 214     (void) view;
 215     (void) c;
 216 #endif /* HAVE_CHARSET */
 217     return 1;
 218 }
 219 
 220 /* --------------------------------------------------------------------------------------------- */
 221 
 222 static gboolean
 223 mcview_ismark (const WView *view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 224 {
 225 #ifdef HAVE_CHARSET
 226     if (view->utf8)
 227         return g_unichar_ismark (c);
 228 #else
 229     (void) view;
 230     (void) c;
 231 #endif /* HAVE_CHARSET */
 232     return FALSE;
 233 }
 234 
 235 /* --------------------------------------------------------------------------------------------- */
 236 
 237 /* actually is_non_spacing_mark_or_enclosing_mark */
 238 static gboolean
 239 mcview_is_non_spacing_mark (const WView *view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 240 {
 241 #ifdef HAVE_CHARSET
 242     if (view->utf8)
 243     {
 244         GUnicodeType type;
 245 
 246         type = g_unichar_type (c);
 247 
 248         return type == G_UNICODE_NON_SPACING_MARK || type == G_UNICODE_ENCLOSING_MARK;
 249     }
 250 #else
 251     (void) view;
 252     (void) c;
 253 #endif /* HAVE_CHARSET */
 254     return FALSE;
 255 }
 256 
 257 /* --------------------------------------------------------------------------------------------- */
 258 
 259 #if 0
 260 static gboolean
 261 mcview_is_spacing_mark (const WView *view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 262 {
 263 #ifdef HAVE_CHARSET
 264     if (view->utf8)
 265         return g_unichar_type (c) == G_UNICODE_SPACING_MARK;
 266 #else
 267     (void) view;
 268     (void) c;
 269 #endif /* HAVE_CHARSET */
 270     return FALSE;
 271 }
 272 #endif /* 0 */
 273 
 274 /* --------------------------------------------------------------------------------------------- */
 275 
 276 static gboolean
 277 mcview_isprint (const WView *view, int c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 278 {
 279 #ifdef HAVE_CHARSET
 280     if (!view->utf8)
 281         c = convert_from_8bit_to_utf_c ((unsigned char) c, view->converter);
 282     return g_unichar_isprint (c);
 283 #else
 284     (void) view;
 285     /* TODO this is very-very buggy by design: ticket 3257 comments 0-1 */
 286     return is_printable (c);
 287 #endif /* HAVE_CHARSET */
 288 }
 289 
 290 /* --------------------------------------------------------------------------------------------- */
 291 
 292 static int
 293 mcview_char_display (const WView *view, int c, char *s)
     /* [previous][next][first][last][top][bottom][index][help]  */
 294 {
 295 #ifdef HAVE_CHARSET
 296     if (mc_global.utf8_display)
 297     {
 298         if (!view->utf8)
 299             c = convert_from_8bit_to_utf_c ((unsigned char) c, view->converter);
 300         if (!g_unichar_isprint (c))
 301             c = '.';
 302         return g_unichar_to_utf8 (c, s);
 303     }
 304     if (view->utf8)
 305     {
 306         if (g_unichar_iswide (c))
 307         {
 308             s[0] = s[1] = '.';
 309             return 2;
 310         }
 311         if (g_unichar_iszerowidth (c))
 312             return 0;
 313         /* TODO the is_printable check below will be broken for this */
 314         c = convert_from_utf_to_current_c (c, view->converter);
 315     }
 316     else
 317     {
 318         /* TODO the is_printable check below will be broken for this */
 319         c = convert_to_display_c (c);
 320     }
 321 #else
 322     (void) view;
 323 #endif /* HAVE_CHARSET */
 324     /* TODO this is very-very buggy by design: ticket 3257 comments 0-1 */
 325     if (!is_printable (c))
 326         c = '.';
 327     *s = c;
 328     return 1;
 329 }
 330 
 331 /* --------------------------------------------------------------------------------------------- */
 332 
 333 /**
 334  * Just for convenience, a common interface in front of mcview_get_utf and mcview_get_byte, so that
 335  * the caller doesn't have to care about utf8 vs 8-bit modes.
 336  *
 337  * Normally: stores c, updates state, returns TRUE.
 338  * At EOF: state is unchanged, c is undefined, returns FALSE.
 339  *
 340  * Just as with mcview_get_utf(), invalid UTF-8 is reported using negative integers.
 341  *
 342  * Also, temporary hack: handle force_max here.
 343  * TODO: move it to lower layers (datasource.c)?
 344  */
 345 static gboolean
 346 mcview_get_next_char (WView *view, mcview_state_machine_t *state, int *c)
     /* [previous][next][first][last][top][bottom][index][help]  */
 347 {
 348     /* Pretend EOF if we reached force_max */
 349     if (view->force_max >= 0 && state->offset >= view->force_max)
 350         return FALSE;
 351 
 352 #ifdef HAVE_CHARSET
 353     if (view->utf8)
 354     {
 355         int char_length = 0;
 356 
 357         if (!mcview_get_utf (view, state->offset, c, &char_length))
 358             return FALSE;
 359         /* Pretend EOF if we crossed force_max */
 360         if (view->force_max >= 0 && state->offset + char_length > view->force_max)
 361             return FALSE;
 362 
 363         state->offset += char_length;
 364         return TRUE;
 365     }
 366 #endif /* HAVE_CHARSET */
 367     if (!mcview_get_byte (view, state->offset, c))
 368         return FALSE;
 369     state->offset++;
 370     return TRUE;
 371 }
 372 
 373 /* --------------------------------------------------------------------------------------------- */
 374 /**
 375  * This function parses the next nroff character and gives it to you along with its desired color,
 376  * so you never have to care about nroff again.
 377  *
 378  * The nroff mode does the backspace trick for every single character (Unicode codepoint). At least
 379  * that's what the GNU groff 1.22 package produces, and that's what less 458 expects. For
 380  * double-wide characters (CJK), still only a single backspace is emitted. For combining accents
 381  * and such, the print-backspace-print step is repeated for the base character and then for each
 382  * accent separately.
 383  *
 384  * So, the right place for this layer is after the bytes are interpreted in UTF-8, but before
 385  * joining a base character with its combining accents.
 386  *
 387  * Normally: stores c and color, updates state, returns TRUE.
 388  * At EOF: state is unchanged, c and color are undefined, returns FALSE.
 389  *
 390  * color can be null if the caller doesn't care.
 391  */
 392 static gboolean
 393 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]  */
 394 {
 395     mcview_state_machine_t state_after_nroff;
 396     int c2, c3;
 397 
 398     if (color != NULL)
 399         *color = VIEW_NORMAL_COLOR;
 400 
 401     if (!view->mode_flags.nroff)
 402         return mcview_get_next_char (view, state, c);
 403 
 404     if (!mcview_get_next_char (view, state, c))
 405         return FALSE;
 406     /* Don't allow nroff formatting around CR, LF, TAB or other special chars */
 407     if (!mcview_isprint (view, *c))
 408         return TRUE;
 409 
 410     state_after_nroff = *state;
 411 
 412     if (!mcview_get_next_char (view, &state_after_nroff, &c2))
 413         return TRUE;
 414     if (c2 != '\b')
 415         return TRUE;
 416 
 417     if (!mcview_get_next_char (view, &state_after_nroff, &c3))
 418         return TRUE;
 419     if (!mcview_isprint (view, c3))
 420         return TRUE;
 421 
 422     if (*c == '_' && c3 == '_')
 423     {
 424         *state = state_after_nroff;
 425         if (color != NULL)
 426             *color =
 427                 state->nroff_underscore_is_underlined ? VIEW_UNDERLINED_COLOR : VIEW_BOLD_COLOR;
 428     }
 429     else if (*c == c3)
 430     {
 431         *state = state_after_nroff;
 432         state->nroff_underscore_is_underlined = FALSE;
 433         if (color != NULL)
 434             *color = VIEW_BOLD_COLOR;
 435     }
 436     else if (*c == '_')
 437     {
 438         *c = c3;
 439         *state = state_after_nroff;
 440         state->nroff_underscore_is_underlined = TRUE;
 441         if (color != NULL)
 442             *color = VIEW_UNDERLINED_COLOR;
 443     }
 444 
 445     return TRUE;
 446 }
 447 
 448 /* --------------------------------------------------------------------------------------------- */
 449 /**
 450  * Get one base character, along with its combining or spacing mark characters.
 451  *
 452  * (A spacing mark is a character that extends the base character's width 1 into a combined
 453  * character of width 2, yet these two character cells should not be separated. E.g. Devanagari
 454  * <U+0939><U+094B>.)
 455  *
 456  * This method exists mainly for two reasons. One is to be able to tell if we fit on the current
 457  * line or need to wrap to the next one. The other is that both slang and ncurses seem to require
 458  * that the character and its combining marks are printed in a single call (or is it just a
 459  * limitation of mc's wrapper to them?).
 460  *
 461  * For convenience, this method takes care of converting CR or CR+LF into LF.
 462  * TODO this should probably happen later, when displaying the file?
 463  *
 464  * Normally: stores cs and color, updates state, returns >= 1 (entries in cs).
 465  * At EOF: state is unchanged, cs and color are undefined, returns 0.
 466  *
 467  * @param view ...
 468  * @param state the parser-formatter state machine's state, updated
 469  * @param cs store the characters here
 470  * @param clen the room available in cs (that is, at most clen-1 combining marks are allowed), must
 471  *   be at least 2
 472  * @param color if non-NULL, store the color here, taken from the first codepoint's color
 473  * @return the number of entries placed in cs, or 0 on EOF
 474  */
 475 static int
 476 mcview_next_combining_char_sequence (WView *view, mcview_state_machine_t *state, int *cs,
     /* [previous][next][first][last][top][bottom][index][help]  */
 477                                      int clen, int *color)
 478 {
 479     int i = 1;
 480 
 481     if (!mcview_get_next_maybe_nroff_char (view, state, cs, color))
 482         return 0;
 483 
 484     /* Process \r and \r\n newlines. */
 485     if (cs[0] == '\r')
 486     {
 487         int cnext;
 488 
 489         mcview_state_machine_t state_after_crlf = *state;
 490         if (mcview_get_next_maybe_nroff_char (view, &state_after_crlf, &cnext, NULL)
 491             && cnext == '\n')
 492             *state = state_after_crlf;
 493         cs[0] = '\n';
 494         return 1;
 495     }
 496 
 497     /* We don't want combining over non-printable characters. This includes '\n' and '\t' too. */
 498     if (!mcview_isprint (view, cs[0]))
 499         return 1;
 500 
 501     if (mcview_ismark (view, cs[0]))
 502     {
 503         if (!state->print_lonely_combining)
 504         {
 505             /* First character is combining. Either just return it, ... */
 506             return 1;
 507         }
 508         else
 509         {
 510             /* or place this (and subsequent combining ones) over a dotted circle. */
 511             cs[1] = cs[0];
 512             cs[0] = BASE_CHARACTER_FOR_LONELY_COMBINING;
 513             i = 2;
 514         }
 515     }
 516 
 517     if (mcview_wcwidth (view, cs[0]) == 2)
 518     {
 519         /* Don't allow combining or spacing mark for wide characters, is this okay? */
 520         return 1;
 521     }
 522 
 523     /* Look for more combining chars. Either at most clen-1 zero-width combining chars,
 524      * or at most 1 spacing mark. Is this logic correct? */
 525     for (; i < clen; i++)
 526     {
 527         mcview_state_machine_t state_after_combining;
 528 
 529         state_after_combining = *state;
 530         if (!mcview_get_next_maybe_nroff_char (view, &state_after_combining, &cs[i], NULL))
 531             return i;
 532         if (!mcview_ismark (view, cs[i]) || !mcview_isprint (view, cs[i]))
 533             return i;
 534         if (g_unichar_type (cs[i]) == G_UNICODE_SPACING_MARK)
 535         {
 536             /* Only allow as the first combining char. Stop processing in either case. */
 537             if (i == 1)
 538             {
 539                 *state = state_after_combining;
 540                 i++;
 541             }
 542             return i;
 543         }
 544         *state = state_after_combining;
 545     }
 546     return i;
 547 }
 548 
 549 /* --------------------------------------------------------------------------------------------- */
 550 /**
 551  * Parse, format and possibly display one visual line of text.
 552  *
 553  * Formatting starts at the given "state" (which encodes the file offset and parser and formatter's
 554  * internal state). In unwrap mode, this should point to the beginning of the paragraph with the
 555  * default state, the additional horizontal scrolling is added here. In wrap mode, this should
 556  * point to the beginning of the line, with the proper state at that point.
 557  *
 558  * In wrap mode, if a line ends in a newline, it is consumed, even if it's exactly at the right
 559  * edge. In unwrap mode, the whole remaining line, including the newline is consumed. Displaying
 560  * the next line should start at "state"'s new value, or if we displayed the bottom line then
 561  * state->offset tells the file offset to be shown in the top bar.
 562  *
 563  * If "row" is offscreen, don't actually display the line but still update "state" and return the
 564  * proper value. This is used by mcview_wrap_move_down to advance in the file.
 565  *
 566  * @param view ...
 567  * @param state the parser-formatter state machine's state, updated
 568  * @param row print to this row
 569  * @param paragraph_ended store TRUE if paragraph ended by newline or EOF, FALSE if wraps to next
 570  *   line
 571  * @param linewidth store the width of the line here
 572  * @return the number of rows, that is, 0 if we were already at EOF, otherwise 1
 573  */
 574 static int
 575 mcview_display_line (WView *view, mcview_state_machine_t *state, int row,
     /* [previous][next][first][last][top][bottom][index][help]  */
 576                      gboolean *paragraph_ended, off_t *linewidth)
 577 {
 578     const WRect *r = &view->data_area;
 579     off_t dpy_text_column = view->mode_flags.wrap ? 0 : view->dpy_text_column;
 580     int col = 0;
 581     int cs[1 + MAX_COMBINING_CHARS];
 582     char str[(1 + MAX_COMBINING_CHARS) * UTF8_CHAR_LEN + 1];
 583     int i, j;
 584 
 585     if (paragraph_ended != NULL)
 586         *paragraph_ended = TRUE;
 587 
 588     if (!view->mode_flags.wrap && (row < 0 || row >= r->lines) && linewidth == NULL)
 589     {
 590         /* Optimization: Fast forward to the end of the line, rather than carefully
 591          * parsing and then not actually displaying it. */
 592         off_t eol;
 593         int retval;
 594 
 595         eol = mcview_eol (view, state->offset);
 596         retval = (eol > state->offset) ? 1 : 0;
 597 
 598         mcview_state_machine_init (state, eol);
 599         return retval;
 600     }
 601 
 602     while (TRUE)
 603     {
 604         int charwidth = 0;
 605         mcview_state_machine_t state_saved;
 606         int n;
 607         int color;
 608 
 609         state_saved = *state;
 610         n = mcview_next_combining_char_sequence (view, state, cs, 1 + MAX_COMBINING_CHARS, &color);
 611         if (n == 0)
 612         {
 613             if (linewidth != NULL)
 614                 *linewidth = col;
 615             return (col > 0) ? 1 : 0;
 616         }
 617 
 618         if (view->search_start <= state->offset && state->offset < view->search_end)
 619             color = VIEW_SELECTED_COLOR;
 620 
 621         if (cs[0] == '\n')
 622         {
 623             /* New line: reset all formatting state for the next paragraph. */
 624             mcview_state_machine_init (state, state->offset);
 625             if (linewidth != NULL)
 626                 *linewidth = col;
 627             return 1;
 628         }
 629 
 630         if (mcview_is_non_spacing_mark (view, cs[0]))
 631         {
 632             /* Lonely combining character. Probably leftover after too many combining chars. Just ignore. */
 633             continue;
 634         }
 635 
 636         /* Nonprintable, or lonely spacing mark */
 637         if ((!mcview_isprint (view, cs[0]) || mcview_ismark (view, cs[0])) && cs[0] != '\t')
 638             cs[0] = '.';
 639 
 640         for (i = 0; i < n; i++)
 641             charwidth += mcview_wcwidth (view, cs[i]);
 642 
 643         /* Adjust the width for TAB. It's handled below along with the normal characters,
 644          * so that it's wrapped consistently with them, and is painted with the proper
 645          * attributes (although currently it can't have a special color). */
 646         if (cs[0] == '\t')
 647         {
 648             charwidth = option_tab_spacing - state->unwrapped_column % option_tab_spacing;
 649             state->print_lonely_combining = TRUE;
 650         }
 651         else
 652             state->print_lonely_combining = FALSE;
 653 
 654         /* In wrap mode only: We're done with this row if the character sequence wouldn't fit.
 655          * Except if at the first column, because then it wouldn't fit in the next row either.
 656          * In this extreme case let the unwrapped code below do its best to display it. */
 657         if (view->mode_flags.wrap && (off_t) col + charwidth > dpy_text_column + (off_t) r->cols
 658             && col > 0)
 659         {
 660             *state = state_saved;
 661             if (paragraph_ended != NULL)
 662                 *paragraph_ended = FALSE;
 663             if (linewidth != NULL)
 664                 *linewidth = col;
 665             return 1;
 666         }
 667 
 668         /* Display, unless outside of the viewport. */
 669         if (row >= 0 && row < r->lines)
 670         {
 671             if ((off_t) col >= dpy_text_column &&
 672                 (off_t) col + charwidth <= dpy_text_column + (off_t) r->cols)
 673             {
 674                 /* The combining character sequence fits entirely in the viewport. Print it. */
 675                 tty_setcolor (color);
 676                 widget_gotoyx (view, r->y + row, r->x + ((off_t) col - dpy_text_column));
 677                 if (cs[0] == '\t')
 678                 {
 679                     for (i = 0; i < charwidth; i++)
 680                         tty_print_char (' ');
 681                 }
 682                 else
 683                 {
 684                     j = 0;
 685                     for (i = 0; i < n; i++)
 686                         j += mcview_char_display (view, cs[i], str + j);
 687                     str[j] = '\0';
 688                     /* This is probably a bug in our tty layer, but tty_print_string
 689                      * normalizes the string, whereas tty_printf doesn't. Don't normalize,
 690                      * since we handle combining characters ourselves correctly, it's
 691                      * better if they are copy-pasted correctly. Ticket 3255. */
 692                     tty_printf ("%s", str);
 693                 }
 694             }
 695             else if ((off_t) col < dpy_text_column && (off_t) col + charwidth > dpy_text_column)
 696             {
 697                 /* The combining character sequence would cross the left edge of the viewport.
 698                  * This cannot happen with wrap mode. Print replacement character(s),
 699                  * or spaces with the correct attributes for partial Tabs. */
 700                 tty_setcolor (color);
 701                 for (i = dpy_text_column;
 702                      i < (off_t) col + charwidth && i < dpy_text_column + (off_t) r->cols; i++)
 703                 {
 704                     widget_gotoyx (view, r->y + row, r->x + (i - dpy_text_column));
 705                     tty_print_anychar ((cs[0] == '\t') ? ' ' : PARTIAL_CJK_AT_LEFT_MARGIN);
 706                 }
 707             }
 708             else if ((off_t) col < dpy_text_column + (off_t) r->cols &&
 709                      (off_t) col + charwidth > dpy_text_column + (off_t) r->cols)
 710             {
 711                 /* The combining character sequence would cross the right edge of the viewport
 712                  * and we're not wrapping. Print replacement character(s),
 713                  * or spaces with the correct attributes for partial Tabs. */
 714                 tty_setcolor (color);
 715                 for (i = col; i < dpy_text_column + (off_t) r->cols; i++)
 716                 {
 717                     widget_gotoyx (view, r->y + row, r->x + (i - dpy_text_column));
 718                     tty_print_anychar ((cs[0] == '\t') ? ' ' : PARTIAL_CJK_AT_RIGHT_MARGIN);
 719                 }
 720             }
 721         }
 722 
 723         col += charwidth;
 724         state->unwrapped_column += charwidth;
 725 
 726         if (!view->mode_flags.wrap && (off_t) col >= dpy_text_column + (off_t) r->cols
 727             && linewidth == NULL)
 728         {
 729             /* Optimization: Fast forward to the end of the line, rather than carefully
 730              * parsing and then not actually displaying it. */
 731             off_t eol;
 732 
 733             eol = mcview_eol (view, state->offset);
 734             mcview_state_machine_init (state, eol);
 735             return 1;
 736         }
 737     }
 738 }
 739 
 740 /* --------------------------------------------------------------------------------------------- */
 741 /**
 742  * Parse, format and possibly display one paragraph (perhaps not from the beginning).
 743  *
 744  * Formatting starts at the given "state" (which encodes the file offset and parser and formatter's
 745  * internal state). In unwrap mode, this should point to the beginning of the paragraph with the
 746  * default state, the additional horizontal scrolling is added here. In wrap mode, this may point
 747  * to the beginning of the line within a paragraph (to display the partial paragraph at the top),
 748  * with the proper state at that point.
 749  *
 750  * Displaying the next paragraph should start at "state"'s new value, or if we displayed the bottom
 751  * line then state->offset tells the file offset to be shown in the top bar.
 752  *
 753  * If "row" is negative, don't display the first abs(row) lines and display the rest from the top.
 754  * This was a nice idea but it's now unused :)
 755  *
 756  * If "row" is too large, don't display the paragraph at all but still return the number of lines.
 757  * This is used when moving upwards.
 758  *
 759  * @param view ...
 760  * @param state the parser-formatter state machine's state, updated
 761  * @param row print starting at this row
 762  * @return the number of rows the paragraphs is wrapped to, that is, 0 if we were already at EOF,
 763  *   otherwise 1 in unwrap mode, >= 1 in wrap mode. We stop when reaching the bottom of the
 764  *   viewport, it's not counted how many more lines the paragraph would occupy
 765  */
 766 static int
 767 mcview_display_paragraph (WView *view, mcview_state_machine_t *state, int row)
     /* [previous][next][first][last][top][bottom][index][help]  */
 768 {
 769     int lines = 0;
 770 
 771     while (TRUE)
 772     {
 773         gboolean paragraph_ended;
 774 
 775         lines += mcview_display_line (view, state, row, &paragraph_ended, NULL);
 776         if (paragraph_ended)
 777             return lines;
 778 
 779         if (row < view->data_area.lines)
 780         {
 781             row++;
 782             /* stop if bottom of screen reached */
 783             if (row >= view->data_area.lines)
 784                 return lines;
 785         }
 786     }
 787 }
 788 
 789 /* --------------------------------------------------------------------------------------------- */
 790 /**
 791  * Recompute dpy_state_top from dpy_start and dpy_paragraph_skip_lines. Clamp
 792  * dpy_paragraph_skip_lines if necessary.
 793  *
 794  * This method should be called in wrap mode after changing one of the parsing or formatting
 795  * properties (e.g. window width, encoding, nroff), or when switching to wrap mode from unwrap or
 796  * hex.
 797  *
 798  * If we stayed within the same paragraph then try to keep the vertical offset within that
 799  * paragraph as well. It might happen though that the paragraph became shorter than our desired
 800  * vertical position, in that case move to its last row.
 801  */
 802 static void
 803 mcview_wrap_fixup (WView *view)
     /* [previous][next][first][last][top][bottom][index][help]  */
 804 {
 805     int lines = view->dpy_paragraph_skip_lines;
 806 
 807     if (!view->dpy_wrap_dirty)
 808         return;
 809     view->dpy_wrap_dirty = FALSE;
 810 
 811     view->dpy_paragraph_skip_lines = 0;
 812     mcview_state_machine_init (&view->dpy_state_top, view->dpy_start);
 813 
 814     while (lines-- != 0)
 815     {
 816         mcview_state_machine_t state_prev;
 817         gboolean paragraph_ended;
 818 
 819         state_prev = view->dpy_state_top;
 820         if (mcview_display_line (view, &view->dpy_state_top, -1, &paragraph_ended, NULL) == 0)
 821             break;
 822         if (paragraph_ended)
 823         {
 824             view->dpy_state_top = state_prev;
 825             break;
 826         }
 827         view->dpy_paragraph_skip_lines++;
 828     }
 829 }
 830 
 831 /* --------------------------------------------------------------------------------------------- */
 832 /*** public functions ****************************************************************************/
 833 /* --------------------------------------------------------------------------------------------- */
 834 
 835 /**
 836  * In both wrap and unwrap modes, dpy_start points to the beginning of the paragraph.
 837  *
 838  * In unwrap mode, start displaying from this position, probably applying an additional horizontal
 839  * scroll.
 840  *
 841  * In wrap mode, an additional dpy_paragraph_skip_lines lines are skipped from the top of this
 842  * paragraph. dpy_state_top contains the position and parser-formatter state corresponding to the
 843  * top left corner so we can just start rendering from here. Unless dpy_wrap_dirty is set in which
 844  * case dpy_state_top is invalid and we need to recompute first.
 845  */
 846 void
 847 mcview_display_text (WView *view)
     /* [previous][next][first][last][top][bottom][index][help]  */
 848 {
 849     const WRect *r = &view->data_area;
 850     int row;
 851     mcview_state_machine_t state;
 852     gboolean again;
 853 
 854     do
 855     {
 856         int n;
 857 
 858         again = FALSE;
 859 
 860         mcview_display_clean (view);
 861         mcview_display_ruler (view);
 862 
 863         if (!view->mode_flags.wrap)
 864             mcview_state_machine_init (&state, view->dpy_start);
 865         else
 866         {
 867             mcview_wrap_fixup (view);
 868             state = view->dpy_state_top;
 869         }
 870 
 871         for (row = 0; row < r->lines; row += n)
 872         {
 873             n = mcview_display_paragraph (view, &state, row);
 874             if (n == 0)
 875             {
 876                 /* In the rare case that displaying didn't start at the beginning
 877                  * of the file, yet there are some empty lines at the bottom,
 878                  * scroll the file and display again. This happens when e.g. the
 879                  * window is made bigger, or the file becomes shorter due to
 880                  * charset change or enabling nroff. */
 881                 if ((view->mode_flags.wrap ? view->dpy_state_top.offset : view->dpy_start) > 0)
 882                 {
 883                     mcview_ascii_move_up (view, r->lines - row);
 884                     again = TRUE;
 885                 }
 886                 break;
 887             }
 888         }
 889     }
 890     while (again);
 891 
 892     view->dpy_end = state.offset;
 893     view->dpy_state_bottom = state;
 894 
 895     tty_setcolor (VIEW_NORMAL_COLOR);
 896     if (mcview_show_eof != NULL && mcview_show_eof[0] != '\0')
 897         while (row < r->lines)
 898         {
 899             widget_gotoyx (view, r->y + row, r->x);
 900             /* TODO: should make it no wider than the viewport */
 901             tty_print_string (mcview_show_eof);
 902             row++;
 903         }
 904 }
 905 
 906 /* --------------------------------------------------------------------------------------------- */
 907 /**
 908  * Move down.
 909  *
 910  * It's very simple. Just invisibly format the next "lines" lines, carefully carrying the formatter
 911  * state in wrap mode. But before each step we need to check if we've already hit the end of the
 912  * file, in that case we can no longer move. This is done by walking from dpy_state_bottom.
 913  *
 914  * Note that this relies on mcview_display_text() setting dpy_state_bottom to its correct value
 915  * upon rendering the screen contents. So don't call this function from other functions (e.g. at
 916  * the bottom of mcview_ascii_move_up()) which invalidate this value.
 917  */
 918 void
 919 mcview_ascii_move_down (WView *view, off_t lines)
     /* [previous][next][first][last][top][bottom][index][help]  */
 920 {
 921     while (lines-- != 0)
 922     {
 923         gboolean paragraph_ended;
 924 
 925         /* See if there's still data below the bottom line, by imaginarily displaying one
 926          * more line. This takes care of reading more data into growbuf, if required.
 927          * If the end position didn't advance, we're at EOF and hence bail out. */
 928         if (mcview_display_line (view, &view->dpy_state_bottom, -1, &paragraph_ended, NULL) == 0)
 929             break;
 930 
 931         /* Okay, there's enough data. Move by 1 row at the top, too. No need to check for
 932          * EOF, that can't happen. */
 933         if (!view->mode_flags.wrap)
 934         {
 935             view->dpy_start = mcview_eol (view, view->dpy_start);
 936             view->dpy_paragraph_skip_lines = 0;
 937             view->dpy_wrap_dirty = TRUE;
 938         }
 939         else
 940         {
 941             mcview_display_line (view, &view->dpy_state_top, -1, &paragraph_ended, NULL);
 942             if (!paragraph_ended)
 943                 view->dpy_paragraph_skip_lines++;
 944             else
 945             {
 946                 view->dpy_start = view->dpy_state_top.offset;
 947                 view->dpy_paragraph_skip_lines = 0;
 948             }
 949         }
 950     }
 951 }
 952 
 953 /* --------------------------------------------------------------------------------------------- */
 954 /**
 955  * Move up.
 956  *
 957  * Unwrap mode: Piece of cake. Wrap mode: If we'd walk back more than the current line offset
 958  * within the paragraph, we need to jump back to the previous paragraph and compute its height to
 959  * see if we start from that paragraph, and repeat this if necessary. Once we're within the desired
 960  * paragraph, we still need to format it from its beginning to know the state.
 961  *
 962  * See the top of this file for comments about MAX_BACKWARDS_WALK_IN_PARAGRAPH.
 963  *
 964  * force_max is a nice protection against the rare extreme case that the file underneath us
 965  * changes, we don't want to endlessly consume a file of maybe full of zeros upon moving upwards.
 966  */
 967 void
 968 mcview_ascii_move_up (WView *view, off_t lines)
     /* [previous][next][first][last][top][bottom][index][help]  */
 969 {
 970     if (!view->mode_flags.wrap)
 971     {
 972         while (lines-- != 0)
 973             view->dpy_start = mcview_bol (view, view->dpy_start - 1, 0);
 974         view->dpy_paragraph_skip_lines = 0;
 975         view->dpy_wrap_dirty = TRUE;
 976     }
 977     else
 978     {
 979         int i;
 980 
 981         while (lines > view->dpy_paragraph_skip_lines)
 982         {
 983             /* We need to go back to the previous paragraph. */
 984             if (view->dpy_start == 0)
 985             {
 986                 /* Oops, we're already in the first paragraph. */
 987                 view->dpy_paragraph_skip_lines = 0;
 988                 mcview_state_machine_init (&view->dpy_state_top, 0);
 989                 return;
 990             }
 991             lines -= view->dpy_paragraph_skip_lines;
 992             view->force_max = view->dpy_start;
 993             view->dpy_start =
 994                 mcview_bol (view, view->dpy_start - 1,
 995                             view->dpy_start - MAX_BACKWARDS_WALK_IN_PARAGRAPH);
 996             mcview_state_machine_init (&view->dpy_state_top, view->dpy_start);
 997             /* This is a tricky way of denoting that we're at the end of the paragraph.
 998              * Normally we'd jump to the next paragraph and reset paragraph_skip_lines. But for
 999              * walking backwards this is exactly what we need. */
1000             view->dpy_paragraph_skip_lines =
1001                 mcview_display_paragraph (view, &view->dpy_state_top, view->data_area.lines);
1002             view->force_max = -1;
1003         }
1004 
1005         /* Okay, we have have dpy_start pointing to the desired paragraph, and we still need to
1006          * walk back "lines" lines from the current "dpy_paragraph_skip_lines" offset. We can't do
1007          * that, so walk from the beginning of the paragraph. */
1008         mcview_state_machine_init (&view->dpy_state_top, view->dpy_start);
1009         view->dpy_paragraph_skip_lines -= lines;
1010         for (i = 0; i < view->dpy_paragraph_skip_lines; i++)
1011             mcview_display_line (view, &view->dpy_state_top, -1, NULL, NULL);
1012     }
1013 }
1014 
1015 /* --------------------------------------------------------------------------------------------- */
1016 
1017 void
1018 mcview_ascii_moveto_bol (WView *view)
     /* [previous][next][first][last][top][bottom][index][help]  */
1019 {
1020     if (!view->mode_flags.wrap)
1021         view->dpy_text_column = 0;
1022 }
1023 
1024 /* --------------------------------------------------------------------------------------------- */
1025 
1026 void
1027 mcview_ascii_moveto_eol (WView *view)
     /* [previous][next][first][last][top][bottom][index][help]  */
1028 {
1029     if (!view->mode_flags.wrap)
1030     {
1031         mcview_state_machine_t state;
1032         off_t linewidth;
1033 
1034         /* Get the width of the topmost paragraph. */
1035         mcview_state_machine_init (&state, view->dpy_start);
1036         mcview_display_line (view, &state, -1, NULL, &linewidth);
1037         view->dpy_text_column = DOZ (linewidth, (off_t) view->data_area.cols);
1038     }
1039 }
1040 
1041 /* --------------------------------------------------------------------------------------------- */
1042 
1043 void
1044 mcview_state_machine_init (mcview_state_machine_t *state, off_t offset)
     /* [previous][next][first][last][top][bottom][index][help]  */
1045 {
1046     memset (state, 0, sizeof (*state));
1047     state->offset = offset;
1048     state->print_lonely_combining = TRUE;
1049 }
1050 
1051 /* --------------------------------------------------------------------------------------------- */

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