|Developer||Dan Lewis and Frank Bracher, Tymshare|
|Dartmouth BASIC, JOSS, CAL|
SUPER BASIC, sometimes SBASIC for short, is an advanced dialect of the BASIC programming language offered on Tymshare's SDS 940 systems starting in 1968 and available well into the 1970s.
Like the Dartmouth BASIC it was based on, SUPER BASIC was a compile and go language, as opposed to an interpreter. In addition to offering most of the commands and functions from Dartmouth BASIC Version 4, in including matrix math commands, SUPER BASIC also included a number of features from the seminal JOSS language developed at Rand Corporation, via Tymshare's version, CAL, and added a variety of new functions, complex numbers as a built-in type, and double precision support.
SUPER BASIC also greatly improved string handling over the rudimentary system in Dartmouth, introducing the
RIGHT string functions, simple string concatenation and other features. These were later used in DEC's BASIC-PLUS, which was later used as the basis for the original Microsoft BASIC that saw widespread use in the 1980s.
The original Dartmouth BASIC was released in 1964 but was largely experimental at the time. It went through several revisions before becoming truly useful with the Fourth Edition when it was ported to the GE 635 machine and was published in 1968. Dartmouth specifically placed the underlying design in the public domain, so that anyone could port it to their platforms and call it BASIC. Its spread was further helped by the tireless efforts of its authors to promote it. However, as the code was designed to run on the DTSS operating system, some porting was required to run it on production systems. This led to a proliferation of versions with minor differences.
Tymshare was formed within the University of California, Berkeley, initially renting out time on the University's computers on off-hours. Tymshare's original BASIC, simply Tymshare BASIC, was based on source code "from elsewhere" in the University, that Dan Lewis began enhancing. Frank Bracher added the routines for file input/output (I/O), which made it far more practical than the original Dartmouth code that relied purely on
DATA statements embedded in the program. Dartmouth's workflow was tape based so loading and saving individual files was not practical and direct I/O was not addressed until later versions. Bracher's I/O code had originally been developed for Tymshare's SUPER FORTRAN offering.
One oft-noted feature of the system was the documentation, written by Caroline Diehl. The manuals were written in a conversational style.
Tymshare maintained SUPER BASIC through the 1970s, but as the market for rented timeshare programming services dwindled the system went into maintenance and Lewis and Bracher left to do SUPER BASIC consulting for those companies still using it. Maintenance within Tymshare passed primarily to Walter Main.
Tymshare filed for a trademark on SUPER BASIC on 7 January 1970, and refreshed it on 17 October 1977, which became the property of McDonnell Douglas in 1984 when the company purchased Tymshare.
Like most BASIC systems of the era, SUPER BASIC had a single command line editor that worked both as an interactive language and a program editor. Commands that were typed without a line number were executed immediately, which they referred to as "direct mode".[a] If the same line was prefixed with a line number, it was instead copied into the program code storage area, known as "indirect mode". New lines were added to the program if the line number was unique, replaced existing lines with the same number, or removed from the program if an existing line number was typed in without any code following it.
Line numbers ran from 0 to 999999. The
DELETE (or short-form
DEL) could be used to delete a range of lines using typical
LIST notation, for instance,
DELETE 5,10-50. The
ENTER command started an automatic line-number system. It took two optional parameters, a starting line number and a step, separated with
BY. The starting number was assumed to be zero if not provided, and the step was 10. For instance,
ENTER would produce 0,10,20,...,
ENTER BY 5 would produce 0,5,10,..., and
ENTER 10 BY 10 would produce 10,20,30...
RENUMBER took three parameters, a new starting line number, a range of lines to renumber (like 20-100) and the step.
Although the built-in editor loaded and saved only the lines in the program itself, the user could edit the resulting text file to add additional commands that would run in direct mode. A common example was to edit a program and add
RUN on its own line at the end of the file. When loaded, the system would see the
RUN and immediately compile and start the program on loading. This is unusual for BASIC systems, although this was commonly used in JOSS.
In keeping with the overall Dartmouth BASIC concept, SUPER BASIC was a compile and go system that compiled the source code when the program was run. SUPER BASIC had two commands for this, the typical
RUN seen in most BASICs, as well as
START which did the same thing. Remarks could be placed anywhere using
SUPER BASIC expanded the
FOR statement in several ways. A minor change was to allow
BY in place of
STEP, and allowed the step to be placed at the end as in most BASICs, or in the middle as in JOSS and other languages. Thus
FOR I=1 TO 10 BY 2 and
FOR I=1 BY 2 TO 10 were both valid. Additionally, SUPER BASIC provided alternate forms of the range definition using
UNTIL, whereas most other languages used completely separate loop structures for these. For instance,
FOR X=1 WHILE X<Y will continue as long as X<Y, while
FOR X=1 UNTIL X<Y stops when the condition is met. As in Microsoft BASIC, multiple loops could end with a single
NEXT I,J, although it did not include the feature of later version of MS where the index variable could be left off entirely. Finally, in JOSS fashion, one could replace the typical range specifier
1 TO 10 with an explicit list of values,
A more major change, following the JOSS model, was the concept of "statement modifiers" that allowed an
FOR to be placed after the statement it controlled. For instance,
PRINT "IT IS" IF X=5 is equivalent to
IF X=5 THEN PRINT "IT IS". This can make some commonly found use-cases easier to understand. It also included the syntactic sugar
UNLESS which was an
IF with the opposite sense; for instance,
PRINT "IT IS NOT FIVE" UNLESS X=5. One could also use a loop in these cases, which made single one-statement loops easy to implement, for instance
PRINT X FOR X=1 TO 10. One could also use a "bare"
UNTIL without the for,
X=X+2 UNTIL X>10. The modifiers could also be ganged,
PRINT "YES" IF A=B UNLESS N=0.
Variable names could consist of one or two letters or one letter and a digit. SUPER BASIC did not require variables to be typed, a variable could hold a number at one point and a string at another, a side-effect of the way they were stored. This required the system to test the variable type at runtime during
In most dialects of BASIC, variables are created on-the-fly as they are encountered in the code, and generally set to zero (or the empty string) when created. This can lead to problems where variables are supposed to be set up by previous code that is not being properly called, but at run time it can be difficult to know if 0 is an uninitialized value or one with the perfectly legal 0 values. SUPER BASIC addressed this with the
VAR command. There were two primary forms,
VAR=ZERO which made all undefined variables automatically get the value zero when accessed, which is the normal pattern for BASIC, and
VAR=UNDEF which would instead cause a "VARIABLE HAS NO VALUE" error to occur when a previously unseen variable was used in a way that attempted to access its value. The later is very useful in debugging scenarios, where the normal behavior can hide the fact that a variable being used in a calculation has not been correctly initialized.
Unless otherwise specified, variables were stored in a 48-bit single precision floating point format with eleven digits of precision. One could also explicitly define a variable as
REAL A, which was the single-precision format. This was not a consideration in other BASICs where some sort of suffix, like
$, indicated the type wherever it was encountered.
When required, a double precision format with seventeen digits, stored in three 24-bit words instead of two, could be used by declaring a variable with
DOUBLE A,B. An existing single precision value or expression could be converted to double using the
DBL(X) function. For instance, one could force an expression to evaluate using double precision using
Likewise, one could declare
INTEGER A to produce a one-word 24-bit integer value.
A more unusual addition was direct support for complex numbers. These were set up in a fashion similar to other variables, using
COMPLEX I,J to set aside two single precision slots. When encountered in programs, other statements like
INPUT would trigger alternative modes that asked for two numbers instead of one, with similar modifications to
READ (used with
CMPLX(X,Y) function, while
IMAG(I) extracted the real and imaginary parts, respectively, into singles. A small number of additional utility functions were also offered.
There were seven basic math operators:
↑for exponents - the exponent is converted to a 12-bit integer
MODfor modulo, the remainder of an integer division
DIVfor integer division
SUPER BASIC's list of mathematical functions was longer than most BASICs, including a series of inverse trigonometric functions and logarithms for base 2 and 10.
RND(X), returns a random number using a fixed sequence, can be seeded with RND(-1) ABS(N), absolute value SQR(N) or SQRT(N), square root SIN COS TAN ASIN ACOS ATN or ATAN ATN/ATAN with two variables, (y,x) calculates y/x and returns ATN of that SINH COSTH TANH LOG LGT/LOG10 LOG2 EXP EXP2 INT, as in BASIC, always truncates downward FIX, similar to INT but simply truncating the decimal ROUND, rounds the value to closest, unlike INT COMP(X,Y) COMPare, combines a subtraction and SGN, so if X>Y=1, X=Y=0, X<y+-1 PDIF(X,Y) Positive DIFference, returns difference (X-Y) if X>Y, 0 otherwise
SUPER BASIC included a number of functions from JOSS as well:
IP(), Integer Part, equivalent to INT FP(), Fraction Part, same as X-INT(X) MAX(...) returns the maximum value from a list of entries MIN(...) returns the minimum
In addition to basic math, SUPER BASIC included array functionality like many other BASIC implementations. One could
DIM A(5,5) to make a two-dimensional array, and as a consequence of the way they were stored, all variables otherwise undeclared were actually DIMed to have ten indexes, so one could
LET B(5)=20 without previously DIMing B.
In contrast with other BASICs, SUPER BASIC allowed one to define the range of one or both of the dimensions, assuming 1 if not defined. So A in the example above has indexes 1..5, but one might also
DIM A(-5:5,0:5) to produce an array that has 11 indexes from -5 to +5 for X, and 0 to +5 for Y. One could also use the
BASE command to change the default, so
BASE 0, for example, makes all dimensions start at 0.
In addition to these traditional BASIC concepts, SUPER BASIC also included most of the matrix math features found in later versions of Dartmouth BASIC. These were invoked by adding the keyword
MAT to the front of other commands. For instance,
MAT A=B*C multiplies all the items in array B by their corresponding item in C, whereas
MAT A=B*5 multiplies all the elements in B by 5. Functions for common matrix operations like inversion and identity were included.
As in most versions of BASIC, SUPER BASIC included the standard set of comparison operators,
<, as well as boolean operators
NOT. In addition,
# could be used as an alternate form of
<>, a form that was found on a number of BASIC implementations in that era. SUPER BASIC also added
EQV for "equivalence" (equals) and
IMP for "implication".
To this basic set, SUPER BASIC also added three new commands for comparing small differences between numbers, these were
=#. The much-greater-than and much-less-than operators compared the values of the two operands, for instance, A and B in the expression
A >> B. If adding B to A results in A being unchanged after the inherent rounding,
>> returned true. Internally this was performed by
=#, the close-to-equals, simply compared both values to an internal meta-variable,
Most dialects of BASIC allow the result of such logical comparisons to be stored in variables, using some internal format to represent the logical value, often 0 for false and 1 or -1 for true. SUPER BASIC also allowed this, which resulted in the somewhat confusing behavior of
LET A=B=5, which, following operator precedence, assigns 5 to B and then returns true or false if A=B. SUPER BASIC also added true logical variables, declared in a similar fashion as doubles or complex, using
LOGICAL A, and other variables could be conveyed to logical using
In contrast to logical comparisons and operators, SUPER BASIC also added a number of bitwise logical operators. These applied a basic logical operation to the individual bits in a word. These included
BEX, for and, or and exclusive or. Additional functions include
RSH(X) for bit-shifting left and right, respectively. To ease the entry of binary values, constants could be entered in octal format[b] by prefixing a number with an "O", like
SUPER BASIC allowed string constants (literals) to be enclosed with single or double quotes, so
PRINT "HELLO, WORLD!" and
PRINT 'HELLO, WIKIPEDIA!' were both valid statements.
In contrast to later dialects of BASIC, one could assign a string to any variable and the
$ signifier was not used, so
A="HELLO, WORLD!" was valid. This could lead to some confusion when a user provided a value combining digits and letters, and SUPER BASIC assumed anything starting with a digit was a number. To guide the system when this might result in confusing input, one could explicitly declare string variables using
STRING A. As with all variables in SUPER BASIC, these could be arrays,
STRING A(5). Additionally, SUPER BASIC added the additional statement
TEXT which took a second parameter to define the length of the string elements, so
TEXT A(12):10 makes an array with 12 elements of 10 characters each, while
TEXT B(5:10):15 is an array of six elements, 5..10, each 15 characters line.
SUPER BASIC included operators for
= for comparison and
+ for concatenation. It included the following functions:
ASC(S), returns the ASCII number for the first character in the string CHAR(N), returns a string with a single ASCII character, same as MS CHR() COMP(A,B), compares two strings, returns -1,0,1 depending on which is "bigger" INDEX(A,B), returns the index of B within A. Optional 3rd parameter is an offset starting point LENGTH(A), length of the string SPACE(X), returns a string consisting of X number of spaces VAL(A), looks through the string for a number and returns it STR(N), converts a number into a string LEFT, as in MS RIGHT SUBSTR, as MS's MID
Typical utility functions are also included:
POS returns the column of the print head POS(X) returns the position in a file TAX(X) moves the print head to column X TAX(X,N) the same in file number N DATE TIME
SUPER BASIC also included pseudo-variables for
DPI, the later being double-precision, as well as the previously mentioned
EPS to represent the smallest possible value.
SUPER BASIC included two forms of print formatting that could be used with the
PRINT IN IMAGE X: used a format string, in this case stored in X, in a fashion similar to what other BASICs implemented using
PRINT USING or the more common examples found in C and its follow-ons. Field type included integers, specified decimal formats, and exponents, as well as strings and text.
% signs indicated a single digit in either an integer or real field, and
# indicated a digit in an E field.
$ could be used to prefix any value.
PRINT IN FORMAT worked generally the same way, the difference being that spaces had to be explicitly defined using
B. Thus the format string "%% BBB %%.%%" would print two numerical values with three spaces between them, whereas if this was an image the "BBB" would be printed out with a space on either side. The form version supported a wider variety of format strings and included items like inline carriage returns, but the examples given in the manuals do not make it clear why there are two such systems when they accomplish the same thing in the end.
Interestingly, the same format commands could be used for
INPUT, not just
SUPER BASIC included a file input/output system based on
INPUT ON X and
PRINT ON X where X is file handle, a number. The number was assigned using
OPEN filename FOR [INPUT|OUTPUT] AS FILE X.
WRITE ON X was provided as an alternative to print, but are identical internally. When complete, the file can be released with
CLOSE X or
CLOSE filename. When working with files, one could read the next-read location using
LOC(X) and change it using
LOCATE 100 ON 2.
POS(X) returned the position within a form if IN was being used.
SIZE(N) returned the file size. The
ENDFILE(X) could be used in loops to test whether the end of the file was reached during reads.
The system also included a function
TEL that returned whether or not there was input waiting in the terminal. SUPER BASIC programs often included code like
100 WAIT(1);IF NOT TEL THEN 100
to wait for user input and test it every second before continuing. Additionally, it included a pseudo-filename
"TEL" that could be opened for reading and writing using
OPEN "TEL" FOR OUTPUT AS 2 and then
WRITE ON 2 "HELLO WORLD".