akbasic/src/renumber.c

/**
 * @file renumber.c
 * @brief RENUMBER: move every line, and rewrite every reference to one.
 *
 * Moving the lines is easy -- source is filed under its line number in
 * `source[]`, so it is a permutation. Rewriting every `GOTO`, `GOSUB`, `RUN`,
 * `RESTORE`, `TRAP` and `COLLISION` target to match is the job, and it is why
 * this was deferred rather than written early: a `RENUMBER` that moved lines
 * without fixing their references would silently break every branch in the
 * program, which is worse than not having the verb at all.
 *
 * The rewrite is textual, and the only thing it has to understand about the rest
 * of the language is where a string literal starts and stops -- `PRINT "GOTO 10"`
 * must come through untouched. That is the same statement-walking the label and
 * DATA prescans do.
 */

#include <ctype.h>
#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <strings.h>

#include <akerror.h>

#include <akbasic/error.h>
#include <akbasic/runtime.h>

/**
 * @brief Verbs whose numeric arguments name a line.
 *
 * `THEN` and `ELSE` are deliberately absent. Commodore BASIC lets `IF X THEN 100`
 * stand for `THEN GOTO 100`; this dialect does not -- the corpus writes
 * `THEN GOTO 100` -- so a number after `THEN` here is an expression, not a target.
 *
 * `LIST` and `DELETE` are absent too, and for a different reason: their
 * arguments are ranges typed at a prompt, not references stored in a program.
 * Renumbering a `DELETE` inside a listing would be rewriting something nobody
 * meant as a branch.
 */
static const char *BRANCH_VERBS[] = { "GOTO", "GOSUB", "RUN", "RESTORE", "TRAP" };
/** @brief How many entries #BRANCH_VERBS has. */
#define BRANCH_VERB_COUNT ((int)(sizeof(BRANCH_VERBS) / sizeof(BRANCH_VERBS[0])))

/**
 * @brief Where a line moved to, or the line itself when it did not move.
 *
 * A target naming a line that does not exist is left alone rather than
 * rewritten: `GOTO 9999` in a program with no line 9999 is already broken, and
 * inventing a destination for it would hide that.
 */
static int64_t mapped(const int64_t *map, int64_t line)
{
    if ( line < 0 || line >= AKBASIC_MAX_SOURCE_LINES ) {
	return line;
    }
    return (map[line] >= 0 ? map[line] : line);
}

/**
 * @brief Copy a run of comma-separated line numbers, rewriting each.
 *
 * `ON X GOTO 100, 200, 300` is why this takes a list rather than one number: the
 * targets follow the `GOTO`, so handling `GOTO` handles `ON` for free.
 *
 * @param map Old line to new line.
 * @param src Reads from here; advanced past what was consumed.
 * @param dest Writes to here; advanced past what was written.
 * @param limit One past the last byte @p dest may write.
 * @return `NULL` on success, otherwise an error context owned by the caller.
 * @throws AKBASIC_ERR_BOUNDS When the rewritten line does not fit.
 */
static akerr_ErrorContext *rewrite_targets(const int64_t *map, const char **src, char **dest, const char *limit)
{
    PREPARE_ERROR(errctx);
    const char *p = *src;
    char *out = *dest;

    for ( ;; ) {
	int64_t line = 0;
	int written = 0;

	while ( *p == ' ' || *p == '\t' ) {
	    FAIL_ZERO_RETURN(errctx, (out < limit), AKBASIC_ERR_BOUNDS,
			     "RENUMBER: a rewritten line does not fit");
	    *out = *p;
	    out += 1;
	    p += 1;
	}
	if ( !isdigit((unsigned char)*p) ) {
	    /*
	     * Not a number: a label, an expression, or nothing at all. Labels are
	     * the reason RENUMBER is survivable in the first place -- a program
	     * written with `GOTO DONE` needs no rewriting and cannot be broken by
	     * one.
	     */
	    break;
	}
	while ( isdigit((unsigned char)*p) ) {
	    line = (line * 10) + (*p - '0');
	    p += 1;
	}
	written = snprintf(out, (size_t)(limit - out), "%" PRId64, mapped(map, line));
	FAIL_ZERO_RETURN(errctx, (written > 0 && out + written < limit), AKBASIC_ERR_BOUNDS,
			 "RENUMBER: a rewritten line does not fit");
	out += written;

	/*
	 * A comma continues the list; anything else ends it. The spaces are
	 * skipped to find out which, and put back if the answer is "ends" --
	 * without that, `THEN GOTO 9 ELSE ...` came back as `THEN GOTO 30ELSE`.
	 */
	{
	    const char *afterdigits = p;

	    while ( *p == ' ' || *p == '\t' ) {
		p += 1;
	    }
	    if ( *p != ',' ) {
		p = afterdigits;
		break;
	    }
	}
	FAIL_ZERO_RETURN(errctx, (out < limit), AKBASIC_ERR_BOUNDS,
			 "RENUMBER: a rewritten line does not fit");
	*out = ',';
	out += 1;
	p += 1;
    }
    *src = p;
    *dest = out;
    SUCCEED_RETURN(errctx);
}

/**
 * @brief Rewrite every branch target in one line of source.
 *
 * @param map Old line to new line.
 * @param code The line to read.
 * @param dest Where the rewritten line goes.
 * @param len Capacity of @p dest.
 * @return `NULL` on success, otherwise an error context owned by the caller.
 * @throws AKBASIC_ERR_BOUNDS When the rewritten line does not fit.
 */
static akerr_ErrorContext *rewrite_line(const int64_t *map, const char *code, char *dest, size_t len)
{
    PREPARE_ERROR(errctx);
    const char *p = code;
    char *out = dest;
    const char *limit = dest + len - 1;
    bool statementstart = true;
    bool instring = false;
    int i = 0;

    while ( *p != '\0' ) {
	size_t verblen = 0;
	bool matched = false;

	FAIL_ZERO_RETURN(errctx, (out < limit), AKBASIC_ERR_BOUNDS,
			 "RENUMBER: a rewritten line does not fit");
	if ( instring ) {
	    instring = (*p != '"');
	    *out = *p;
	    out += 1;
	    p += 1;
	    continue;
	}
	if ( *p == '"' ) {
	    /* A string literal is copied through untouched: `PRINT "GOTO 10"`. */
	    instring = true;
	    statementstart = false;
	    *out = *p;
	    out += 1;
	    p += 1;
	    continue;
	}
	if ( *p == ':' ) {
	    statementstart = true;
	    *out = *p;
	    out += 1;
	    p += 1;
	    continue;
	}
	if ( *p == ' ' || *p == '\t' ) {
	    *out = *p;
	    out += 1;
	    p += 1;
	    continue;
	}

	for ( i = 0; i < BRANCH_VERB_COUNT; i++ ) {
	    verblen = strlen(BRANCH_VERBS[i]);
	    if ( strncasecmp(p, BRANCH_VERBS[i], verblen) == 0 &&
		 !isalnum((unsigned char)p[verblen]) ) {
		matched = true;
		break;
	    }
	}
	/*
	 * A branch verb may appear anywhere a statement may, and `GOTO` also
	 * follows `THEN`, `ELSE` and `ON X` -- none of which is a statement
	 * start. So the match is not gated on statementstart; what protects
	 * `A$ = "GOTO"` is the string check above, and what protects a variable
	 * called `GOTOX#` is the alphanumeric check here.
	 */
	if ( matched ) {
	    FAIL_ZERO_RETURN(errctx, (out + verblen < (size_t)(limit - dest) + dest),
			     AKBASIC_ERR_BOUNDS, "RENUMBER: a rewritten line does not fit");
	    memcpy(out, p, verblen);
	    out += verblen;
	    p += verblen;
	    PASS(errctx, rewrite_targets(map, &p, &out, limit));
	    statementstart = false;
	    continue;
	}

	/*
	 * COLLISION's handler is its *second* argument, so the list rewrite
	 * cannot be pointed at it directly. Copy the type and the comma, then
	 * rewrite what follows.
	 */
	if ( strncasecmp(p, "COLLISION", 9) == 0 && !isalnum((unsigned char)p[9]) ) {
	    memcpy(out, p, 9);
	    out += 9;
	    p += 9;
	    while ( *p != '\0' && *p != ',' && *p != ':' ) {
		FAIL_ZERO_RETURN(errctx, (out < limit), AKBASIC_ERR_BOUNDS,
				 "RENUMBER: a rewritten line does not fit");
		*out = *p;
		out += 1;
		p += 1;
	    }
	    if ( *p == ',' ) {
		*out = ',';
		out += 1;
		p += 1;
		PASS(errctx, rewrite_targets(map, &p, &out, limit));
	    }
	    statementstart = false;
	    continue;
	}

	statementstart = false;
	*out = *p;
	out += 1;
	p += 1;
    }
    *out = '\0';
    (void)statementstart;
    SUCCEED_RETURN(errctx);
}

akerr_ErrorContext *akbasic_renumber(akbasic_Runtime *obj, int64_t newstart, int64_t increment, int64_t oldstart)
{
    PREPARE_ERROR(errctx);
    static int64_t map[AKBASIC_MAX_SOURCE_LINES];
    static akbasic_SourceLine rewritten[AKBASIC_MAX_SOURCE_LINES];
    int64_t next = newstart;
    int64_t i = 0;

    FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL runtime in renumber");
    FAIL_ZERO_RETURN(errctx, (increment > 0), AKBASIC_ERR_VALUE,
		     "RENUMBER's increment must be positive, not %" PRId64, increment);
    FAIL_ZERO_RETURN(errctx, (newstart > 0), AKBASIC_ERR_VALUE,
		     "RENUMBER cannot start at line %" PRId64, newstart);

    for ( i = 0; i < AKBASIC_MAX_SOURCE_LINES; i++ ) {
	map[i] = -1;
    }

    /*
     * Build the whole map before touching anything. A rewrite needs to know
     * where *every* line ended up, including ones it has not reached yet --
     * a backward `GOTO` is as common as a forward one.
     */
    for ( i = 0; i < AKBASIC_MAX_SOURCE_LINES; i++ ) {
	if ( obj->source[i].code[0] == '\0' || i < oldstart ) {
	    continue;
	}
	FAIL_ZERO_RETURN(errctx, (next < AKBASIC_MAX_SOURCE_LINES), AKBASIC_ERR_BOUNDS,
			 "RENUMBER: line %" PRId64 " would become %" PRId64 ", past the %d line limit",
			 i, next, AKBASIC_MAX_SOURCE_LINES - 1);
	/*
	 * A renumbered line must not land on a kept one. Refused rather than
	 * overwritten: losing a line to a renumbering is not recoverable.
	 */
	FAIL_ZERO_RETURN(errctx, (next >= oldstart || obj->source[next].code[0] == '\0'),
			 AKBASIC_ERR_VALUE,
			 "RENUMBER: line %" PRId64 " would become %" PRId64 ", which already exists",
			 i, next);
	map[i] = next;
	next += increment;
    }

    memset(rewritten, 0, sizeof(rewritten));
    for ( i = 0; i < AKBASIC_MAX_SOURCE_LINES; i++ ) {
	int64_t target = 0;

	if ( obj->source[i].code[0] == '\0' ) {
	    continue;
	}
	/*
	 * Every line is rewritten, not just the moved ones: a line before
	 * `oldstart` can branch into the region that moved.
	 */
	target = mapped(map, i);
	PASS(errctx, rewrite_line(map, obj->source[i].code,
				  rewritten[target].code, sizeof(rewritten[target].code)));
	rewritten[target].lineno = target;
    }

    memcpy(obj->source, rewritten, sizeof(obj->source));
    SUCCEED_RETURN(errctx);
}