mined1.c

操作系统源代码

/*
 * Part one of the mined editor.
 */

/*
 * Author: Michiel Huisjes.
 * 
 * 1. General remarks.
 * 
 *   Mined is a screen editor designed for the MINIX operating system.
 *   It is meant to be used on files not larger than 50K and to be fast.
 *   When mined starts up, it reads the file into its memory to minimize
 *   disk access. The only time that disk access is needed is when certain
 *   save, write or copy commands are given.
 * 
 *   Mined has the style of Emacs or Jove, that means that there are no modes.
 *   Each character has its own entry in an 256 pointer to function array,
 *   which is called when that character is typed. Only ASCII characters are
 *   connected with a function that inserts that character at the current
 *   location in the file. Two execptions are <linefeed> and <tab> which are
 *   inserted as well. Note that the mapping between commands and functions
 *   called is implicit in the table. Changing the mapping just implies
 *   changing the pointers in this table.
 * 
 *   The display consists of SCREENMAX + 1 lines and XMAX + 1 characters. When
 *   a line is larger (or gets larger during editing) than XBREAK characters,
 *   the line is either shifted SHIFT_SIZE characters to the left (which means
 *   that the first SHIFT_SIZE characters are not printed) or the end of the
 *   line is marked with the SHIFT_MARK character and the rest of the line is
 *   not printed.  A line can never exceed MAX_CHARS characters. Mined will
 *   always try to keep the cursor on the same line and same (relative)
 *   x-coordinate if nothing changed. So if you scroll one line up, the cursor
 *   stays on the same line, or when you move one line down, the cursor will
 *   move to the same place on the line as it was on the previous.
 *   Every character on the line is available for editing including the
 *   linefeed at the the of the line. When the linefeed is deleted, the current
 *   line and the next line are joined. The last character of the file (which
 *   is always a linefeed) can never be deleted.
 *   The bottomline (as indicated by YMAX + 1) is used as a status line during
 *   editing. This line is usually blank or contains information mined needs
 *   during editing. This information (or rather questions) is displayed in
 *   reverse video.
 * 
 *   The terminal modes are changed completely. All signals like start/stop,
 *   interrupt etc. are unset. The only signal that remains is the quit signal.
 *   The quit signal (^\) is the general abort signal for mined. Typing a ^\
 *   during searching or when mined is asking for filenames, etc. will abort
 *   the function and mined will return to the main loop.  Sending a quit
 *   signal during the main loop will abort the session (after confirmation)
 *   and the file is not (!) saved.
 *   The session will also be aborted when an unrecoverable error occurs. E.g
 *   when there is no more memory available. If the file has been modified,
 *   mined will ask if the file has to be saved or not.
 *   If there is no more space left on the disk, mined will just give an error 
 *   message and continue.
 * 
 *   The number of system calls are minized. This is done to keep the editor
 *   as fast as possible. I/O is done in SCREEN_SIZE reads/writes. Accumulated
 *   output is also flushed at the end of each character typed.
 * 
 * 2. Regular expressions
 *   
 *   Mined has a build in regular expression matcher, which is used for
 *   searching and replace routines. A regular expression consists of a
 *   sequence of:
 * 
 *      1. A normal character matching that character.
 *      2. A . matching any character.
 *      3. A ^ matching the begin of a line.
 *      4. A $ (as last character of the pattern) mathing the end of a line.
 *      5. A \<character> matching <character>.
 *      6. A number of characters enclosed in [] pairs matching any of these
 *        characters. A list of characters can be indicated by a '-'. So
 *        [a-z] matches any letter of the alphabet. If the first character
 *        after the '[' is a '^' then the set is negated (matching none of
 *        the characters). 
 *        A ']', '^' or '-' can be escaped by putting a '\' in front of it.
 *        Of course this means that a \ must be represented by \\.
 *      7. If one of the expressions as described in 1-6 is followed by a
 *        '*' than that expressions matches a sequence of 0 or more of
 *        that expression.
 * 
 *   Parsing of regular expression is done in two phases. In the first phase
 *   the expression is compiled into a more comprehensible form. In the second
 *   phase the actual matching is done. For more details see 3.6.
 * 
 * 
 * 3. Implementation of mined.
 * 
 *   3.1 Data structures.
 * 
 *      The main data structures are as follows. The whole file is kept in a
 *      double linked list of lines. The LINE structure looks like this:
 * 
 *         typedef struct Line {
 *              struct Line *next;
 *              struct Line *prev;
 *              char *text;
 *              unsigned char shift_count;
 *         } LINE;
 * 
 *      Each line entry contains a pointer to the next line, a pointer to the
 *      previous line and a pointer to the text of that line. A special field
 *      shift_count contains the number of shifts (in units of SHIFT_SIZE)
 *      that is performed on that line. The total size of the structure is 7
 *      bytes so a file consisting of 1000 empty lines will waste a lot of
 *      memory. A LINE structure is allocated for each line in the file. After
 *      that the number of characters of the line is counted and sufficient
 *      space is allocated to store them (including a linefeed and a '\0').
 *      The resulting address is assigned to the text field in the structure.
 * 
 *      A special structure is allocated and its address is assigned to the
 *      variable header as well as the variable tail. The text field of this
 *      structure is set to NIL_PTR. The tail->prev of this structure points
 *      to the last LINE of the file and the header->next to the first LINE.
 *      Other LINE *variables are top_line and bot_line which point to the
 *      first line resp. the last line on the screen.
 *      Two other variables are important as well. First the LINE *cur_line,
 *      which points to the LINE currently in use and the char *cur_text,
 *      which points to the character at which the cursor stands.
 *      Whenever an ASCII character is typed, a new line is build with this
 *      character inserted. Then the old data space (pointed to by
 *      cur_line->text) is freed, data space for the new line is allocated and
 *      assigned to cur_line->text.
 * 
 *      Two global variables called x and y represent the x and y coordinates
 *      from the cursor. The global variable nlines contains the number of
 *      lines in the file. Last_y indicates the maximum y coordinate of the
 *      screen (which is usually SCREENMAX).
 * 
 *      A few strings must be initialized by hand before compiling mined.
 *      These string are enter_string, which is printed upon entering mined,
 *      rev_video (turn on reverse video), normal_video, rev_scroll (perform a
 *      reverse scroll) and pos_string. The last string should hold the
 *      absolute position string to be printed for cursor motion. The #define
 *      X_PLUS and Y_PLUS should contain the characters to be added to the
 *      coordinates x and y (both starting at 0) to finish cursor positioning.
 * 
 *   3.2 Starting up.
 *      
 *      Mined can be called with or without argument and the function
 *      load_file () is called with these arguments. load_file () checks
 *      if the file exists if it can be read and if it is writable and
 *      sets the writable flag accordingly. If the file can be read, 
 *      load_file () reads a line from the file and stores this line into
 *      a structure by calling install_line () and line_insert () which
 *      installs the line into the double linked list, until the end of the
 *      file is reached.
 *      Lines are read by the function get_line (), which buffers the
 *      reading in blocks of SCREEN_SIZE. Load_file () also initializes the
 *      LINE *variables described above.
 * 
 *   3.3 Moving around.
 * 
 *      Several commands are implemented for moving through the file.
 *      Moving up (UP), down (DN) left (LF) and right (RT) are done by the
 *      arrow keys. Moving one line below the screen scrolls the screen one
 *      line up. Moving one line above the screen scrolls the screen one line
 *      down. The functions forward_scroll () and reverse_scroll () take care
 *      of that.
 *      Several other move functions exist: move to begin of line (BL), end of
 *      line (EL) top of screen (HIGH), bottom of screen (LOW), top of file
 *      (HO), end of file (EF), scroll one page down (PD), scroll one page up
 *      (PU), scroll one line down (SD), scroll one line up (SU) and move to a
 *      certain line number (GOTO).
 *      Two functions called MN () and MP () each move one word further or 
 *      backwards. A word is a number of non-blanks seperated by a space, a
 *      tab or a linefeed.
 * 
 *   3.4 Modifying text.
 * 
 *      The modifying commands can be separated into two modes. The first
 *      being inserting text, and the other deleting text. Two functions are
 *      created for these purposes: insert () and delete (). Both are capable
 *      of deleting or inserting large amounts of text as well as one
 *      character. Insert () must be given the line and location at which
 *      the text must be inserted. Is doesn't make any difference whether this
 *      text contains linefeeds or not. Delete () must be given a pointer to
 *      the start line, a pointer from where deleting should start on that
 *      line and the same information about the end position. The last
 *      character of the file will never be deleted. Delete () will make the
 *      necessary changes to the screen after deleting, but insert () won't.
 *      The functions for modifying text are: insert one char (S), insert a
 *      file (file_insert (fd)), insert a linefeed and put cursor back to
 *      end of line (LIB), delete character under the cursor (DCC), delete
 *      before cursor (even linefeed) (DPC), delete next word (DNW), delete
 *      previous word (DPC) and delete to end of line (if the cursor is at
 *      a linefeed delete line) (DLN).
 * 
 *   3.5 Yanking.
 * 
 *      A few utilities are provided for yanking pieces of text. The function
 *      MA () marks the current position in the file. This is done by setting 
 *      LINE *mark_line and char *mark_text to the current position. Yanking
 *      of text can be done in two modes. The first mode just copies the text
 *      from the mark to the current position (or visa versa) into a buffer
 *      (YA) and the second also deletes the text (DT). Both functions call
 *      the function set_up () with the delete flag on or off. Set_up ()
 *      checks if the marked position is still a valid one (by using
 *      check_mark () and legal ()), and then calls the function yank () with
 *      a start and end position in the file. This function copies the text
 *      into a scratch_file as indicated by the variable yank_file. This
 *      scratch_file is made uniq by the function scratch_file (). At the end
 *      of copying yank will (if necessary) delete the text. A global flag
 *      called yank_status keeps track of the buffer (or file) status. It is
 *      initialized on NOT_VALID and set to EMPTY (by set_up ()) or VALID (by
 *      yank ()). Several things can be done with the buffer. It can be
 *      inserted somewhere else in the file (PT) or it can be copied into
 *      another file (WB), which will be prompted for.
 * 
 *   3.6 Search and replace routines.
 * 
 *      Searching for strings and replacing strings are done by regular
 *      expressions. For any expression the function compile () is called
 *      with as argument the expression to compile. Compile () returns a
 *      pointer to a structure which looks like this:
 * 
 *         typedef struct regex {
 *              union {
 *                    char *err_mess;
 *                    int *expression;
 *              } result;
 *              char status;
 *              char *start_ptr;
 *              char *end_ptr;
 *         } REGEX;
 *      
 *    If something went wrong during compiling (e.g. an illegal expression
 *    was given), the function reg_error () is called, which sets the status
 *    field to REG_ERROR and the err_mess field to the error message. If the
 *    match must be anchored at the beginning of the line (end of line), the
 *    status field is set to BEGIN_LINE (END_LINE). If none of these special
 *    cases are true, the field is set to 0 and the function finished () is
 *    called.  Finished () allocates space to hold the compiled expression
 *    and copies this expression into the expression field of the union
 *    (bcopy ()). Matching is done by the routines match() and line_check().
 *    Match () takes as argument the REGEX *program, a pointer to the
 *    startposition on the current line, and a flag indicating FORWARD or
 *    REVERSE search.  Match () checks out the whole file until a match is
 *    found. If match is found it returns a pointer to the line in which the
 *    match was found else it returns a NIL_LINE. Line_check () takes the
 *    same arguments, but return either MATCH or NO_MATCH.
 *    During checking, the start_ptr and end_ptr fields of the REGEX
 *    structure are assigned to the start and end of the match. 
 *    Both functions try to find a match by walking through the line
 *    character by character. For each possibility, the function
 *    check_string () is called with as arguments the REGEX *program and the
 *    string to search in. It starts walking through the expression until
 *    the end of the expression or the end of the string is reached.
 *    Whenever a * is encountered, this position of the string is marked,
 *    the maximum number of matches are performed and the function star ()
 *    is called in order to try to find the longest match possible. Star ()
 *    takes as arguments the REGEX program, the current position of the
 *    string, the marked position and the current position of the expression
 *    Star () walks from the current position of the string back to the
 *    marked position, and calls string_check () in order to find a match.
 *    It returns MATCH or NO_MATCH, just as string_check () does.
 *    Searching is now easy. Both search routines (forward (SF) and
 *    backwards search (SR)) call search () with an apropiate message and a
 *    flag indicating FORWARD or REVERSE search. Search () will get an
 *    expression from the user by calling get_expression(). Get_expression()
 *    returns a pointer to a REGEX structure or NIL_REG upon errors and
 *    prompts for the expression. If no expression if given, the previous is
 *    used instead. After that search will call match (), and if a match is
 *    found, we can move to that place in the file by the functions find_x()
 *    and find_y () which will find display the match on the screen.
 *    Replacing can be done in two ways. A global replace (GR) or a line
 *    replace (LR). Both functions call change () with a message an a flag
 *    indicating global or line replacement. Change () will prompt for the
 *    expression and for the replacement. Every & in the replacement pattern
 *    means substitute the match instead. An & can be escaped by a \. When
 *    a match is found, the function substitute () will perform the
 *    substitution.
 * 
 *  3.6 Miscellaneous commands.
 * 
 *    A few commands haven't be discussed yet. These are redraw the screen
 *    (RD) fork a shell (SH), print file status (FS), write file to disc
 *    (WT), insert a file at current position (IF), leave editor (XT) and
 *    visit another file (VI). The last two functions will check if the file
 *    has been modified. If it has, they will ask if you want to save the
 *    file by calling ask_save ().
 *    The function ESC () will repeat a command n times. It will prompt for
 *    the number. Aborting the loop can be done by sending the ^\ signal.
 * 
 *  3.7 Utility functions.
 * 
 *    Several functions exists for internal use. First allocation routines:
 *    alloc (bytes) and newline () will return a pointer to free data space
 *    if the given size. If there is no more memory available, the function
 *    panic () is called.
 *    Signal handling: The only signal that can be send to mined is the 
 *    SIGQUIT signal. This signal, functions as a general abort command.
 *    Mined will abort if the signal is given during the main loop. The 
 *    function abort_mined () takes care of that.
 *    Panic () is a function with as argument a error message. It will print
 *    the message and the error number set by the kernel (errno) and will
 *    ask if the file must be saved or not. It resets the terminal
 *    (raw_mode ()) and exits.
 *    String handling routines like copy_string(to, from), length_of(string)
 *    and build_string (buffer, format, arg1, arg2, ...). The latter takes
 *    a description of the string out out the format field and puts the
 *    result in the buffer. (It works like printf (3), but then into a
 *    string). The functions status_line (string1, string2), error (string1,
 *    string2), clear_status () and bottom_line () all print information on
 *    the status line.
 *    Get_string (message, buffer) reads a string and getchar () reads one
 *    character from the terminal.
 *    Num_out ((long) number) prints the number into a 11 digit field
 *    without leading zero's. It returns a pointer to the resulting string.
 *    File_status () prints all file information on the status line.
 *    Set_cursor (x, y) prints the string to put the cursor at coordinates
 *    x and y.
 *    Output is done by four functions: writeline(fd,string), clear_buffer()
 *    write_char (fd, c) and flush_buffer (fd). Three defines are provided
 *    to write on filedescriptor STD_OUT (terminal) which is used normally:
 *    string_print (string), putchar (c) and flush (). All these functions
 *    use the global I/O buffer screen and the global index for this array
 *    called out_count. In this way I/O can be buffered, so that reads or
 *    writes can be done in blocks of SCREEN_SIZE size.
 *    The following functions all handle internal line maintenance. The
 *    function proceed (start_line, count) returns the count'th line after
 *    start_line.  If count is negative, the count'th line before the
 *    start_line is returned. If header or tail is encountered then that
 *    will be returned. Display (x, y, start_line, count) displays count
 *    lines starting at coordinates [x, y] and beginning at start_line. If
 *    the header or tail is encountered, empty lines are displayed instead.
 *    The function reset (head_line, ny) reset top_line, last_y, bot_line,
 *    cur_line and y-coordinate. This is not a neat way to do the
 *    maintenance, but it sure saves a lot of code. It is usually used in
 *    combination with display ().
 *    Put_line(line, offset, clear_line), prints a line (skipping characters
 *    according to the line->shift_size field) until XBREAK - offset
 *    characters are printed or a '\n' is encountered. If clear_line is
 *	  TRUE, spaces are printed until XBREAK - offset characters.
 *	  Line_print (line) is a #define from put_line (line, 0, TRUE).
 *    Moving is done by the functions move_to (x, y), move_addres (address)
 *    and move (x, adress, y). This function is the most important one in
 *    mined. New_y must be between 0 and last_y, new_x can be about
 *    anything, address must be a pointer to an character on the current
 *    line (or y). Move_to () first adjust the y coordinate together with
 *    cur_line. If an address is given, it finds the corresponding
 *    x-coordinate. If an new x-coordinate was given, it will try to locate
 *    the corresponding character. After that it sets the shift_count field
 *    of cur_line to an apropiate number according to new_x. The only thing
 *    left to do now is to assign the new values to cur_line, cur_text, x
 *    and y.
 * 
 * 4. Summary of commands.
 *  
 *  CURSOR MOTION
 *    up-arrow  Move cursor 1 line up.  At top of screen, reverse scroll
 *    down-arrow  Move cursor 1 line down.  At bottom, scroll forward.
 *    left-arrow  Move cursor 1 character left or to end of previous line
 *    right-arrow Move cursor 1 character right or to start of next line
 *    CTRL-A   Move cursor to start of current line
 *    CTRL-Z   Move cursor to end of current line
 *    CTRL-^   Move cursor to top of screen
 *    CTRL-_   Move cursor to bottom of screen
 *    CTRL-F   Forward to start of next word (even to next line)
 *    CTRL-B   Backward to first character of previous word
 *   
 *  SCREEN MOTION
 *    Home key  Move cursor to first character of file
 *    End key   Move cursor to last character of file
 *    PgUp    Scroll backward 1 page. Bottom line becomes top line
 *    PgD    Scroll backward 1 page. Top line becomes bottom line
 *    CTRL-D   Scroll screen down one line (reverse scroll)
 *    CTRL-U   Scroll screen up one line (forward scroll)
 *   
 *  MODIFYING TEXT
 *    ASCII char  Self insert character at cursor
 *    tab    Insert tab at cursor
 *    backspace  Delete the previous char (left of cursor), even line feed
 *    Del    Delete the character under the cursor
 *    CTRL-N   Delete next word
 *    CTRL-P   Delete previous word
 *    CTRL-O   Insert line feed at cursor and back up 1 character
 *    CTRL-T   Delete tail of line (cursor to end); if empty, delete line
 *    CTRL-@   Set the mark (remember the current location)
 *    CTRL-K   Delete text from the mark to current position save on file
 *    CTRL-C   Save the text from the mark to the current position
 *    CTRL-Y   Insert the contents of the save file at current position
 *    CTRL-Q   Insert the contents of the save file into a new file
 *    CTRL-G   Insert a file at the current position
 *   
 *  MISCELLANEOUS
 *    CTRL-E   Erase and redraw the screen
 *    CTRL-V   Visit file (read a new file); complain if old one changed
 *    CTRL-W   Write the current file back to the disk
 *    numeric +  Search forward (prompt for regular expression)
 *    numeric -  Search backward (prompt for regular expression)
 *    numeric 5  Print the current status of the file
 *    CTRL-R   (Global) Replace str1 by str2 (prompts for each string)
 *    CTRL-L   (Line) Replace string1 by string2
 *    CTRL-S   Fork off a shell and wait for it to finish
 *    CTRL-X   EXIT (prompt if file modified)
 *    CTRL-]   Go to a line. Prompts for linenumber
 *    CTRL-\   Abort whatever editor was doing and start again
 *    escape key  Repeat a command count times; (prompts for count)
 */

/*  ========================================================================  *
 *				Utilities				      *	
 *  ========================================================================  */

#include "mined.h"
#include <signal.h>
#include <termios.h>
#include <limits.h>
#include <errno.h>
#include <sys/wait.h>
#include <sys/ioctl.h>
#if __STDC__
#include <stdarg.h>
#else
#include <varargs.h>
#endif

extern int errno;
int ymax = YMAX;
int screenmax = SCREENMAX;


/*
 * Print file status.
 */
void FS()
{
  fstatus(file_name[0] ? "" : "[buffer]", -1L);
}

/*
 * Visit (edit) another file. If the file has been modified, ask the user if
 * he wants to save it.
 */
void VI()
{
  char new_file[LINE_LEN];	/* Buffer to hold new file name */

  if (modified == TRUE && ask_save() == ERRORS)
  	return;
  
/* Get new file name */
  if (get_file("Visit file:", new_file) == ERRORS)
  	return;

/* Free old linked list, initialize global variables and load new file */
  initialize();
#ifdef UNIX
  tputs(CL, 0, _putchar);
#else
  string_print (enter_string);
#endif /* UNIX */
  load_file(new_file[0] == '\0' ? NIL_PTR : new_file);
}

/*
 * Write file in core to disc.
 */
int WT()
{
  register LINE *line;
  register long count = 0L;	/* Nr of chars written */
  char file[LINE_LEN];		/* Buffer for new file name */
  int fd;				/* Filedescriptor of file */

  if (modified == FALSE) {
	error ("Write not necessary.", NIL_PTR);
	return FINE;
  }

/* Check if file_name is valid and if file can be written */
  if (file_name[0] == '\0' || writable == FALSE) {
  	if (get_file("Enter file name:", file) != FINE)
  		return ERRORS;
  	copy_string(file_name, file);		/* Save file name */
  }
  if ((fd = creat(file_name, 0644)) < 0) {	/* Empty file */
  	error("Cannot create ", file_name);
  	writable = FALSE;
  	return ERRORS;
  }
  else
  	writable = TRUE;

  clear_buffer();

  status_line("Writing ", file_name);
  for (line = header->next; line != tail; line = line->next) {
	if (line->shift_count & DUMMY) {
		if (line->next == tail && line->text[0] == '\n')
			continue;
	}
  	if (writeline(fd, line->text) == ERRORS) {
  		count = -1L;
  		break;