# Ocean Interpreter - Stoney Creek version
-Ocean is intended to be an compiled language, so this interpreter is
+Ocean is intended to be a compiled language, so this interpreter is
not targeted at being the final product. It is, rather, an intermediate
-stage, and fills that role in two distinct ways.
+stage and fills that role in two distinct ways.
Firstly, it exists as a platform to experiment with the early language
design. An interpreter is easy to write and easy to get working, so
- "blocks" of multiple statements.
- `pass`: a statement which does nothing.
- - expressions: `+`, `-`, `*`, `/` can apply to numbers and `++` can
+ - expressions: `+`, `-`, `*`, `/`, `%` can apply to numbers and `++` can
catenate strings. `and`, `or`, `not` manipulate Booleans, and
normal comparison operators can work on all three types.
- `print`: will print the values in a list of expressions.
for validating the parsing.
So the main requirements of the interpreter are:
-- Parse the program, possible with tracing
-- Analyse the parsed program to ensure consistency
-- print the program
-- execute the program
+- Parse the program, possibly with tracing,
+- Analyse the parsed program to ensure consistency,
+- Print the program,
+- Execute the program.
This is all performed by a single C program extracted with
`parsergen`.
can contain multiple programs This is effected with the `--section`
option.
+This code must be compiled with `-fplan9-extensions` so that anonymous
+structures can be used.
+
###### File: oceani.mk
myCFLAGS := -Wall -g -fplan9-extensions
struct token_config config;
char *file_name;
int parse_error;
+ struct exec *prog;
## parse context
};
},
};
int doprint=0, dotrace=0, doexec=1, brackets=0;
- struct exec **prog;
int opt;
while ((opt = getopt_long(argc, argv, options, long_options, NULL))
!= -1) {
argv[optind]);
exit(1);
}
+
+ ## context initialization
+
if (section) {
struct section *ss;
for (ss = s; ss; ss = ss->next) {
break;
}
if (ss)
- prog = parse_oceani(ss->code, &context.config,
- dotrace ? stderr : NULL);
+ parse_oceani(ss->code, &context.config,
+ dotrace ? stderr : NULL);
else {
fprintf(stderr, "oceani: cannot find section %s\n",
section);
exit(1);
}
} else
- prog = parse_oceani(s->code, &context.config,
- dotrace ? stderr : NULL);
- if (!prog) {
- fprintf(stderr, "oceani: fatal parser error.\n");
+ parse_oceani(s->code, &context.config,
+ dotrace ? stderr : NULL);
+ if (!context.prog) {
+ fprintf(stderr, "oceani: no program found.\n");
context.parse_error = 1;
}
- if (prog && doprint)
- print_exec(*prog, 0, brackets);
- if (prog && doexec && !context.parse_error) {
- if (!analyse_prog(*prog, &context)) {
+ if (context.prog && doprint)
+ print_exec(context.prog, 0, brackets);
+ if (context.prog && doexec && !context.parse_error) {
+ if (!analyse_prog(context.prog, &context)) {
fprintf(stderr, "oceani: type error in program - not running.\n");
exit(1);
}
- interp_prog(*prog, argv+optind+1);
+ interp_prog(context.prog, argv+optind+1);
}
- if (prog) {
- free_exec(*prog);
- free(prog);
+ if (context.prog) {
+ free_exec(context.prog);
}
while (s) {
struct section *t = s->next;
free(s);
s = t;
}
- ## free context
+ ## free context vars
+ ## free context types
exit(context.parse_error ? 1 : 0);
}
### Analysis
-These four requirements of parse, analyse, print, interpret apply to
+The four requirements of parse, analyse, print, interpret apply to
each language element individually so that is how most of the code
will be structured.
Three of the four are fairly self explanatory. The one that requires
a little explanation is the analysis step.
-The current language design does not require (or even allow) the types
-of variables to be declared, but they must still have a single type.
-Different operations impose different requirements on the variables,
-for example addition requires both arguments to be numeric, and
-assignment requires the variable on the left to have the same type as
-the expression on the right.
+The current language design does not require the types of variables to
+be declared, but they must still have a single type. Different
+operations impose different requirements on the variables, for example
+addition requires both arguments to be numeric, and assignment
+requires the variable on the left to have the same type as the
+expression on the right.
Analysis involves propagating these type requirements around and
consequently setting the type of each variable. If any requirements
#### Error reporting
When analysis discovers an inconsistency it needs to report an error;
-just refusing to run the code esure that the error doesn't cascade,
+just refusing to run the code ensures that the error doesn't cascade,
but by itself it isn't very useful. A clear understand of the sort of
error message that are useful will help guide the process of analysis.
will detect that one argument is not a number and the usage of `hello`
will detect that a number was wanted, but not provided. In this
(early) version of the language, we will generate error reports at
-multiple locations, to the use of `hello` will report an error and
+multiple locations, so the use of `hello` will report an error and
explain were the value was set, and the addition will report an error
and say why numbers are needed. To be able to report locations for
errors, each language element will need to record a file location
of an error message indicates one location in the file, and up to 2
types. So we provide a `printf`-like function which takes a format, a
language (a `struct exec` which has not yet been introduced), and 2
-types. "`$1`" reports the first type, "`$2`" reports the second. We
+types. "`%1`" reports the first type, "`%2`" reports the second. We
will need a function to print the location, once we know how that is
-stored.
+stored. As will be explained later, there are sometimes extra rules for
+type matching and they might affect error messages, we need to pass those
+in too.
+
+As well as type errors, we sometimes need to report problems with
+tokens, which might be unexpected or might name a type that has not
+been defined. For these we have `tok_err()` which reports an error
+with a given token. Each of the error functions sets the flag in the
+context so indicate that parsing failed.
###### forward decls
static void type_err(struct parse_context *c,
char *fmt, struct exec *loc,
- enum vtype t1, enum vtype t2)
+ struct type *t1, int rules, struct type *t2)
{
fprintf(stderr, "%s:", c->file_name);
fput_loc(loc, stderr);
}
fmt++;
switch (*fmt) {
- case '%': fputc(*fmt, stderr); break;
- default: fputc('?', stderr); break;
+ case '%': fputc(*fmt, stderr); break; // NOTEST
+ default: fputc('?', stderr); break; // NOTEST
case '1':
- fputs(vtype_names[t1], stderr);
+ type_print(t1, stderr);
break;
case '2':
- fputs(vtype_names[t2], stderr);
+ type_print(t2, stderr);
break;
## format cases
}
c->parse_error = 1;
}
+ static void tok_err(struct parse_context *c, char *fmt, struct token *t)
+ {
+ fprintf(stderr, "%s:%d:%d: %s: %.*s\n", c->file_name, t->line, t->col, fmt,
+ t->txt.len, t->txt.txt);
+ c->parse_error = 1;
+ }
+
## Data Structures
One last introductory step before detailing the language elements and
There are two key objects that we need to work with: executable
elements which comprise the program, and values which the program
works with. Between these are the variables in their various scopes
-which hold the values.
+which hold the values, and types which classify the values stored and
+manipulatd by executables.
-### Values
+### Types
+
+Values come in a wide range of types, with more likely to be added.
+Each type needs to be able to parse and print its own values (for
+convenience at least) as well as to compare two values, at least for
+equality and possibly for order. For now, values might need to be
+duplicated and freed, though eventually such manipulations will be
+better integrated into the language.
-Values can be numbers, which we represent as multi-precision
-fractions, strings, Booleans and labels. When analysing the program
-we also need to allow for places where no value is meaningful
-(`Vnone`) and where we don't know what type to expect yet (`Vunknown`
-which can be anything and `Vnolabel` which can be anything except a
-label). A 2 character 'tail' is included in each value as the scanner
-wants to parse that from the end of numbers and we need somewhere to
-put it. It is currently ignored but one day might allow for
-e.g. "imaginary" numbers.
+Rather than requiring every numeric type to support all numeric
+operations (add, multiple, etc), we allow types to be able to present
+as one of a few standard types: integer, float, and fraction. The
+existance of these conversion functions enable types to determine if
+they are compatible with other types.
+
+Named type are stored in a simple linked list. Objects of each type are "values"
+which are often passed around by value.
+
+###### ast
+
+ struct value {
+ struct type *type;
+ union {
+ ## value union fields
+ };
+ };
+
+ struct type {
+ struct text name;
+ struct type *next;
+ struct value (*init)(struct type *type);
+ struct value (*prepare)(struct type *type);
+ struct value (*parse)(struct type *type, char *str);
+ void (*print)(struct value val);
+ void (*print_type)(struct type *type, FILE *f);
+ int (*cmp_order)(struct value v1, struct value v2);
+ int (*cmp_eq)(struct value v1, struct value v2);
+ struct value (*dup)(struct value val);
+ void (*free)(struct value val);
+ int (*compat)(struct type *this, struct type *other);
+ long long (*to_int)(struct value *v);
+ double (*to_float)(struct value *v);
+ int (*to_mpq)(mpq_t *q, struct value *v);
+ union {
+ ## type union fields
+ };
+ };
+
+###### parse context
+
+ struct type *typelist;
+
+###### ast functions
+
+ static struct type *find_type(struct parse_context *c, struct text s)
+ {
+ struct type *l = c->typelist;
+
+ while (l &&
+ text_cmp(l->name, s) != 0)
+ l = l->next;
+ return l;
+ }
+
+ static struct type *add_type(struct parse_context *c, struct text s,
+ struct type *proto)
+ {
+ struct type *n;
+
+ n = calloc(1, sizeof(*n));
+ *n = *proto;
+ n->name = s;
+ n->next = c->typelist;
+ c->typelist = n;
+ return n;
+ }
+
+ static void free_type(struct type *t)
+ {
+ /* The type is always a reference to something in the
+ * context, so we don't need to free anything.
+ */
+ }
+
+ static void free_value(struct value v)
+ {
+ if (v.type)
+ v.type->free(v);
+ }
+
+ static int type_compat(struct type *require, struct type *have, int rules)
+ {
+ if ((rules & Rboolok) && have == Tbool)
+ return 1;
+ if ((rules & Rnolabel) && have == Tlabel)
+ return 0;
+ if (!require || !have)
+ return 1;
+
+ if (require->compat)
+ return require->compat(require, have);
+
+ return require == have;
+ }
+
+ static void type_print(struct type *type, FILE *f)
+ {
+ if (!type)
+ fputs("*unknown*type*", f);
+ else if (type->name.len)
+ fprintf(f, "%.*s", type->name.len, type->name.txt);
+ else if (type->print_type)
+ type->print_type(type, f);
+ else
+ fputs("*invalid*type*", f); // NOTEST
+ }
+
+ static struct value val_prepare(struct type *type)
+ {
+ struct value rv;
+
+ if (type)
+ return type->prepare(type);
+ rv.type = type;
+ return rv;
+ }
+
+ static struct value val_init(struct type *type)
+ {
+ struct value rv;
+
+ if (type)
+ return type->init(type);
+ rv.type = type;
+ return rv;
+ }
+
+ static struct value dup_value(struct value v)
+ {
+ if (v.type)
+ return v.type->dup(v);
+ return v;
+ }
+
+ static int value_cmp(struct value left, struct value right)
+ {
+ if (left.type && left.type->cmp_order)
+ return left.type->cmp_order(left, right);
+ if (left.type && left.type->cmp_eq)
+ return left.type->cmp_eq(left, right);
+ return -1;
+ }
+
+ static void print_value(struct value v)
+ {
+ if (v.type && v.type->print)
+ v.type->print(v);
+ else
+ printf("*Unknown*"); // NOTEST
+ }
+
+ static struct value parse_value(struct type *type, char *arg)
+ {
+ struct value rv;
+
+ if (type && type->parse)
+ return type->parse(type, arg);
+ rv.type = NULL; // NOTEST
+ return rv; // NOTEST
+ }
+
+###### forward decls
+
+ static void free_value(struct value v);
+ static int type_compat(struct type *require, struct type *have, int rules);
+ static void type_print(struct type *type, FILE *f);
+ static struct value val_init(struct type *type);
+ static struct value dup_value(struct value v);
+ static int value_cmp(struct value left, struct value right);
+ static void print_value(struct value v);
+ static struct value parse_value(struct type *type, char *arg);
+
+###### free context types
+
+ while (context.typelist) {
+ struct type *t = context.typelist;
+
+ context.typelist = t->next;
+ free(t);
+ }
+
+#### Base Types
+
+Values of the base types can be numbers, which we represent as
+multi-precision fractions, strings, Booleans and labels. When
+analysing the program we also need to allow for places where no value
+is meaningful (type `Tnone`) and where we don't know what type to
+expect yet (type is `NULL`).
Values are never shared, they are always copied when used, and freed
when no longer needed.
When propagating type information around the program, we need to
-determine if two types are compatible, where `Vunknown` is compatible
-which anything, and `Vnolabel` is compatible with anything except a
-label. A separate funtion to encode this rule will simplify some code
-later.
-
-When assigning command line arguments to variable, we need to be able
+determine if two types are compatible, where type `NULL` is compatible
+with anything. There are two special cases with type compatibility,
+both related to the Conditional Statement which will be described
+later. In some cases a Boolean can be accepted as well as some other
+primary type, and in others any type is acceptable except a label (`Vlabel`).
+A separate function encode these cases will simplify some code later.
+
+When assigning command line arguments to variables, we need to be able
to parse each type from a string.
###### includes
myLDLIBS := libnumber.o libstring.o -lgmp
LDLIBS := $(filter-out $(myLDLIBS),$(LDLIBS)) $(myLDLIBS)
-###### ast
- struct value {
- enum vtype {Vnolabel, Vunknown, Vnone, Vstr, Vnum, Vbool, Vlabel} vtype;
- union {
- struct text str;
- mpq_t num;
- int bool;
- void *label;
- };
- char tail[2];
- };
+###### type union fields
+ enum vtype {Vnone, Vstr, Vnum, Vbool, Vlabel} vtype;
- char *vtype_names[] = {"nolabel", "unknown", "none", "string",
- "number", "Boolean", "label"};
+###### value union fields
+ struct text str;
+ mpq_t num;
+ int bool;
+ void *label;
###### ast functions
- static void free_value(struct value v)
+ static void _free_value(struct value v)
{
- switch (v.vtype) {
- case Vnone:
- case Vnolabel:
- case Vunknown: break;
+ switch (v.type->vtype) {
+ case Vnone: break;
case Vstr: free(v.str.txt); break;
case Vnum: mpq_clear(v.num); break;
case Vlabel:
}
}
- static int vtype_compat(enum vtype require, enum vtype have, int bool_permitted)
- {
- if (bool_permitted && have == Vbool)
- return 1;
- switch (require) {
- case Vnolabel:
- return have != Vlabel;
- case Vunknown:
- return 1;
- default:
- return have == Vunknown || require == have;
- }
- }
-
###### value functions
- static void val_init(struct value *val, enum vtype type)
+ static struct value _val_prepare(struct type *type)
{
- val->vtype = type;
- switch(type) {
- case Vnone:abort();
- case Vnolabel:
- case Vunknown: break;
+ struct value rv;
+
+ rv.type = type;
+ switch(type->vtype) {
+ case Vnone:
+ break;
case Vnum:
- mpq_init(val->num); break;
+ memset(&rv.num, 0, sizeof(rv.num));
+ break;
case Vstr:
- val->str.txt = malloc(1);
- val->str.len = 0;
+ rv.str.txt = NULL;
+ rv.str.len = 0;
break;
case Vbool:
- val->bool = 0;
+ rv.bool = 0;
break;
case Vlabel:
- val->label = val;
+ rv.label = NULL;
break;
}
+ return rv;
}
- static struct value dup_value(struct value v)
+ static struct value _val_init(struct type *type)
{
struct value rv;
- rv.vtype = v.vtype;
- switch (rv.vtype) {
- case Vnone:
- case Vnolabel:
- case Vunknown: break;
+
+ rv.type = type;
+ switch(type->vtype) {
+ case Vnone: // NOTEST
+ break; // NOTEST
+ case Vnum:
+ mpq_init(rv.num); break;
+ case Vstr:
+ rv.str.txt = malloc(1);
+ rv.str.len = 0;
+ break;
+ case Vbool:
+ rv.bool = 0;
+ break;
+ case Vlabel: // NOTEST
+ rv.label = NULL; // NOTEST
+ break; // NOTEST
+ }
+ return rv;
+ }
+
+ static struct value _dup_value(struct value v)
+ {
+ struct value rv;
+ rv.type = v.type;
+ switch (rv.type->vtype) {
+ case Vnone: // NOTEST
+ break; // NOTEST
case Vlabel:
rv.label = v.label;
break;
return rv;
}
- static int value_cmp(struct value left, struct value right)
+ static int _value_cmp(struct value left, struct value right)
{
int cmp;
- if (left.vtype != right.vtype)
- return left.vtype - right.vtype;
- switch (left.vtype) {
+ if (left.type != right.type)
+ return left.type - right.type; // NOTEST
+ switch (left.type->vtype) {
case Vlabel: cmp = left.label == right.label ? 0 : 1; break;
case Vnum: cmp = mpq_cmp(left.num, right.num); break;
case Vstr: cmp = text_cmp(left.str, right.str); break;
case Vbool: cmp = left.bool - right.bool; break;
- case Vnone:
- case Vnolabel:
- case Vunknown: cmp = 0;
+ case Vnone: cmp = 0; // NOTEST
}
return cmp;
}
- static struct text text_join(struct text a, struct text b)
- {
- struct text rv;
- rv.len = a.len + b.len;
- rv.txt = malloc(rv.len);
- memcpy(rv.txt, a.txt, a.len);
- memcpy(rv.txt+a.len, b.txt, b.len);
- return rv;
- }
-
- static void print_value(struct value v)
+ static void _print_value(struct value v)
{
- switch (v.vtype) {
- case Vunknown:
- printf("*Unknown*"); break;
- case Vnone:
- case Vnolabel:
- printf("*no-value*"); break;
- case Vlabel:
- printf("*label-%p*", v.label); break;
+ switch (v.type->vtype) {
+ case Vnone: // NOTEST
+ printf("*no-value*"); break; // NOTEST
+ case Vlabel: // NOTEST
+ printf("*label-%p*", v.label); break; // NOTEST
case Vstr:
printf("%.*s", v.str.len, v.str.txt); break;
case Vbool:
}
}
- static int parse_value(struct value *vl, char *arg)
+ static struct value _parse_value(struct type *type, char *arg)
{
+ struct value val;
struct text tx;
int neg = 0;
- switch(vl->vtype) {
- case Vnolabel:
- case Vlabel:
- case Vunknown:
- case Vnone:
- return 0;
+ char tail[3] = "";
+
+ val.type = type;
+ switch(type->vtype) {
+ case Vlabel: // NOTEST
+ case Vnone: // NOTEST
+ val.type = NULL; // NOTEST
+ break; // NOTEST
case Vstr:
- vl->str.len = strlen(arg);
- vl->str.txt = malloc(vl->str.len);
- memcpy(vl->str.txt, arg, vl->str.len);
+ val.str.len = strlen(arg);
+ val.str.txt = malloc(val.str.len);
+ memcpy(val.str.txt, arg, val.str.len);
break;
case Vnum:
if (*arg == '-') {
arg++;
}
tx.txt = arg; tx.len = strlen(tx.txt);
- if (number_parse(vl->num, vl->tail, tx) == 0)
- mpq_init(vl->num);
+ if (number_parse(val.num, tail, tx) == 0)
+ mpq_init(val.num);
else if (neg)
- mpq_neg(vl->num, vl->num);
+ mpq_neg(val.num, val.num);
+ if (tail[0]) {
+ printf("Unsupported suffix: %s\n", arg);
+ val.type = NULL;
+ }
break;
case Vbool:
if (strcasecmp(arg, "true") == 0 ||
strcmp(arg, "1") == 0)
- vl->bool = 1;
+ val.bool = 1;
else if (strcasecmp(arg, "false") == 0 ||
strcmp(arg, "0") == 0)
- vl->bool = 0;
+ val.bool = 0;
else {
printf("Bad bool: %s\n", arg);
- return 0;
+ val.type = NULL;
}
break;
}
- return 1;
+ return val;
+ }
+
+ static void _free_value(struct value v);
+
+ static struct type base_prototype = {
+ .init = _val_init,
+ .prepare = _val_prepare,
+ .parse = _parse_value,
+ .print = _print_value,
+ .cmp_order = _value_cmp,
+ .cmp_eq = _value_cmp,
+ .dup = _dup_value,
+ .free = _free_value,
+ };
+
+ static struct type *Tbool, *Tstr, *Tnum, *Tnone, *Tlabel;
+
+###### ast functions
+ static struct type *add_base_type(struct parse_context *c, char *n, enum vtype vt)
+ {
+ struct text txt = { n, strlen(n) };
+ struct type *t;
+
+ t = add_type(c, txt, &base_prototype);
+ t->vtype = vt;
+ return t;
}
+###### context initialization
+
+ Tbool = add_base_type(&context, "Boolean", Vbool);
+ Tstr = add_base_type(&context, "string", Vstr);
+ Tnum = add_base_type(&context, "number", Vnum);
+ Tnone = add_base_type(&context, "none", Vnone);
+ Tlabel = add_base_type(&context, "label", Vlabel);
+
### Variables
Variables are scoped named values. We store the names in a linked
Scopes in parallel branches can be partially merged. More
specifically, if a given name is declared in both branches of an
-if/else then it's scope is a candidate for merging. Similarly if
+if/else then its scope is a candidate for merging. Similarly if
every branch of an exhaustive switch (e.g. has an "else" clause)
declares a given name, then the scopes from the branches are
candidates for merging.
Note that names declared inside a loop (which is only parallel to
itself) are never visible after the loop. Similarly names defined in
scopes which are not parallel, such as those started by `for` and
-`switch`, are never visible after the scope. Only variable defined in
+`switch`, are never visible after the scope. Only variables defined in
both `then` and `else` (including the implicit then after an `if`, and
excluding `then` used with `for`) and in all `case`s and `else` of a
`switch` or `while` can be visible beyond the `if`/`switch`/`while`.
least to the end of the immediately containing block and conditionally
in any larger containing block which does not declare the name in some
other way. Importantly, the conditional scope extension happens even
-if the label is only used in parallel branch of a conditional -- when
-used in one branch it is treated as having been declared in all
+if the label is only used in one parallel branch of a conditional --
+when used in one branch it is treated as having been declared in all
branches.
Merge candidates are tentatively visible beyond the end of the
To push a new frame *before* any code in the frame is parsed, we need a
grammar reduction. This is most easily achieved with a grammar
-element which derives the empty string, and created the new scope when
+element which derives the empty string, and creates the new scope when
it is recognized. This can be placed, for example, between a keyword
like "if" and the code following it.
- "in scope". This is the case between the declaration of the
variable and the end of the containing block, and also between
- the usage with affirms a merge and the end of the block.
+ the usage with affirms a merge and the end of that block.
The scope depth is not greater than the current parse context scope
nest depth. When the block of that depth closes, the state will
}
}
-###### free context
+###### free context vars
while (context.varlist) {
struct binding *b = context.varlist;
v = t->previous;
free_value(t->val);
+ if (t->min_depth == 0)
+ free_exec(t->where_decl);
free(t);
}
}
v->scope = InScope;
v->in_scope = c->in_scope;
c->in_scope = v;
- val_init(&v->val, Vunknown);
+ v->val = val_prepare(NULL);
return v;
}
else if (v->previous &&
v->previous->scope == PendingScope)
v->scope = PendingScope;
- else if (v->val.vtype == Vlabel)
+ else if (v->val.type == Tlabel)
v->scope = PendingScope;
else if (v->name->var == v)
v->scope = OutScope;
for (v2 = v;
v2 && v2->scope == PendingScope;
v2 = v2->previous)
- if (v2->val.vtype != Vlabel)
+ if (v2->val.type != Tlabel)
v2->scope = OutScope;
break;
case OutScope: break;
}
break;
case CloseSequential:
- if (v->val.vtype == Vlabel)
+ if (v->val.type == Tlabel)
v->scope = PendingScope;
switch (v->scope) {
case InScope:
for (v2 = v;
v2 && v2->scope == PendingScope;
v2 = v2->previous)
- if (v2->val.vtype == Vlabel) {
+ if (v2->val.type == Tlabel) {
v2->scope = CondScope;
v2->min_depth = c->scope_depth;
} else
executables. This allows for expressions and lists etc. Other times
an executable is something quite specific like a constant or variable
name. So we define a `struct exec` to be a general executable with a
-type, and a `struct binode` which is a subclass of `exec` and forms a
-node in a binary tree and holding an operation. There will be other
+type, and a `struct binode` which is a subclass of `exec`, forms a
+node in a binary tree, and holds an operation. There will be other
subclasses, and to access these we need to be able to `cast` the
`exec` into the various other types.
static int __fput_loc(struct exec *loc, FILE *f)
{
+ if (!loc)
+ return 0; // NOTEST
if (loc->line >= 0) {
fprintf(f, "%d:%d: ", loc->line, loc->column);
return 1;
static void fput_loc(struct exec *loc, FILE *f)
{
if (!__fput_loc(loc, f))
- fprintf(f, "??:??: ");
+ fprintf(f, "??:??: "); // NOTEST
}
Each different type of `exec` node needs a number of functions
#### Freeing
The parser generator requires a `free_foo` function for each struct
-that stores attributes and they will be `exec`s of subtypes there-of.
+that stores attributes and they will be `exec`s and subtypes there-of.
So we need `free_exec` which can handle all the subtypes, and we need
`free_binode`.
static void print_exec(struct exec *e, int indent, int bracket)
{
if (!e)
- return;
+ return; // NOTEST
switch (e->type) {
case Xbinode:
print_binode(cast(binode, e), indent, bracket); break;
As discussed, analysis involves propagating type requirements around
the program and looking for errors.
-So `propagate_types` is passed an expected type (being a `vtype`
-together with a `bool_permitted` flag) that the `exec` is expected to
-return, and returns the type that it does return, either of which can
-be `Vunknown`. An `ok` flag is passed by reference. It is set to `0`
-when an error is found, and `2` when any change is made. If it
-remains unchanged at `1`, then no more propagation is needed.
+So `propagate_types` is passed an expected type (being a `struct type`
+pointer together with some `val_rules` flags) that the `exec` is
+expected to return, and returns the type that it does return, either
+of which can be `NULL` signifying "unknown". An `ok` flag is passed
+by reference. It is set to `0` when an error is found, and `2` when
+any change is made. If it remains unchanged at `1`, then no more
+propagation is needed.
+
+###### ast
+
+ enum val_rules {Rnolabel = 1<<0, Rboolok = 1<<1, Rnoconstant = 2<<1};
+
+###### format cases
+ case 'r':
+ if (rules & Rnolabel)
+ fputs(" (labels not permitted)", stderr);
+ break;
###### core functions
- static enum vtype propagate_types(struct exec *prog, struct parse_context *c, int *ok,
- enum vtype type, int bool_permitted)
+ static struct type *propagate_types(struct exec *prog, struct parse_context *c, int *ok,
+ struct type *type, int rules)
{
- enum vtype t;
+ struct type *t;
if (!prog)
- return Vnone;
+ return Tnone;
switch (prog->type) {
case Xbinode:
}
## propagate exec cases
}
- return Vnone;
+ return Tnone;
}
#### Interpreting
which needs to look at command line arguments. The `program` will be
interpreted separately.
-Each `exec` can return a value, which may be `Vnone` but shouldn't be `Vunknown`.
+Each `exec` can return a value, which may be `Tnone` but must be non-NULL;
###### core functions
+ struct lrval {
+ struct value val, *lval;
+ };
+
+ static struct lrval _interp_exec(struct exec *e);
+
static struct value interp_exec(struct exec *e)
{
- struct value rv;
- rv.vtype = Vnone;
- if (!e)
- return rv;
+ struct lrval ret = _interp_exec(e);
+
+ if (ret.lval)
+ return dup_value(*ret.lval);
+ else
+ return ret.val;
+ }
+
+ static struct value *linterp_exec(struct exec *e)
+ {
+ struct lrval ret = _interp_exec(e);
+
+ return ret.lval;
+ }
+
+ static struct lrval _interp_exec(struct exec *e)
+ {
+ struct lrval ret;
+ struct value rv, *lrv = NULL;
+ rv.type = Tnone;
+ if (!e) {
+ ret.lval = lrv;
+ ret.val = rv;
+ return ret;
+ }
switch(e->type) {
case Xbinode:
{
struct binode *b = cast(binode, e);
- struct value left, right;
- left.vtype = right.vtype = Vnone;
+ struct value left, right, *lleft;
+ left.type = right.type = Tnone;
switch (b->op) {
## interp binode cases
}
}
## interp exec cases
}
- return rv;
+ ret.lval = lrv;
+ ret.val = rv;
+ return ret;
+ }
+
+### Complex types
+
+Now that we have the shape of the interpreter in place we can add some
+complex types and connected them in to the data structures and the
+different phases of parse, analyse, print, interpret.
+
+For now, just arrays.
+
+#### Arrays
+
+Arrays can be declared by giving a size and a type, as `[size]type' so
+`freq:[26]number` declares `freq` to be an array of 26 numbers. The
+size can be an arbitrary expression which is evaluated when the name
+comes into scope.
+
+Arrays cannot be assigned. When pointers are introduced we will also
+introduce array slices which can refer to part or all of an array -
+the assignment syntax will create a slice. For now, an array can only
+ever be referenced by the name it is declared with. It is likely that
+a "`copy`" primitive will eventually be define which can be used to
+make a copy of an array with controllable depth.
+
+###### type union fields
+
+ struct {
+ int size;
+ struct variable *vsize;
+ struct type *member;
+ } array;
+
+###### value union fields
+ struct {
+ struct value *elmnts;
+ } array;
+
+###### value functions
+
+ static struct value array_prepare(struct type *type)
+ {
+ struct value ret;
+
+ ret.type = type;
+ ret.array.elmnts = NULL;
+ return ret;
+ }
+
+ static struct value array_init(struct type *type)
+ {
+ struct value ret;
+ int i;
+
+ ret.type = type;
+ if (type->array.vsize) {
+ mpz_t q;
+ mpz_init(q);
+ mpz_tdiv_q(q, mpq_numref(type->array.vsize->val.num),
+ mpq_denref(type->array.vsize->val.num));
+ type->array.size = mpz_get_si(q);
+ mpz_clear(q);
+ }
+ ret.array.elmnts = calloc(type->array.size,
+ sizeof(ret.array.elmnts[0]));
+ for (i = 0; ret.array.elmnts && i < type->array.size; i++)
+ ret.array.elmnts[i] = val_init(type->array.member);
+ return ret;
+ }
+
+ static void array_free(struct value val)
+ {
+ int i;
+
+ if (val.array.elmnts)
+ for (i = 0; i < val.type->array.size; i++)
+ free_value(val.array.elmnts[i]);
+ free(val.array.elmnts);
+ }
+
+ static int array_compat(struct type *require, struct type *have)
+ {
+ if (have->compat != require->compat)
+ return 0;
+ /* Both are arrays, so we can look at details */
+ if (!type_compat(require->array.member, have->array.member, 0))
+ return 0;
+ if (require->array.vsize == NULL && have->array.vsize == NULL)
+ return require->array.size == have->array.size;
+
+ return require->array.vsize == have->array.vsize;
+ }
+
+ static void array_print_type(struct type *type, FILE *f)
+ {
+ fputs("[", f);
+ if (type->array.vsize) {
+ struct binding *b = type->array.vsize->name;
+ fprintf(f, "%.*s]", b->name.len, b->name.txt);
+ } else
+ fprintf(f, "%d]", type->array.size);
+ type_print(type->array.member, f);
+ }
+
+ static struct type array_prototype = {
+ .prepare = array_prepare,
+ .init = array_init,
+ .print_type = array_print_type,
+ .compat = array_compat,
+ .free = array_free,
+ };
+
+###### type grammar
+
+ | [ NUMBER ] Type ${
+ $0 = calloc(1, sizeof(struct type));
+ *($0) = array_prototype;
+ $0->array.member = $<4;
+ $0->array.vsize = NULL;
+ {
+ struct parse_context *c = config2context(config);
+ char tail[3];
+ mpq_t num;
+ if (number_parse(num, tail, $2.txt) == 0)
+ tok_err(c, "error: unrecognised number", &$2);
+ else if (tail[0])
+ tok_err(c, "error: unsupported number suffix", &$2);
+ else {
+ $0->array.size = mpz_get_ui(mpq_numref(num));
+ if (mpz_cmp_ui(mpq_denref(num), 1) != 0) {
+ tok_err(c, "error: array size must be an integer",
+ &$2);
+ } else if (mpz_cmp_ui(mpq_numref(num), 1UL << 30) >= 0)
+ tok_err(c, "error: array size is too large",
+ &$2);
+ mpq_clear(num);
+ }
+ $0->next= c->anon_typelist;
+ c->anon_typelist = $0;
+ }
+ }$
+
+ | [ IDENTIFIER ] Type ${ {
+ struct parse_context *c = config2context(config);
+ struct variable *v = var_ref(c, $2.txt);
+
+ if (!v)
+ tok_err(config2context(config), "error: name undeclared", &$2);
+ else if (!v->constant)
+ tok_err(config2context(config), "error: array size must be a constant", &$2);
+
+ $0 = calloc(1, sizeof(struct type));
+ *($0) = array_prototype;
+ $0->array.member = $<4;
+ $0->array.size = 0;
+ $0->array.vsize = v;
+ $0->next= c->anon_typelist;
+ c->anon_typelist = $0;
+ } }$
+
+###### parse context
+
+ struct type *anon_typelist;
+
+###### free context types
+
+ while (context.anon_typelist) {
+ struct type *t = context.anon_typelist;
+
+ context.anon_typelist = t->next;
+ free(t);
+ }
+
+###### Binode types
+ Index,
+
+###### variable grammar
+
+ | Variable [ Expression ] ${ {
+ struct binode *b = new(binode);
+ b->op = Index;
+ b->left = $<1;
+ b->right = $<3;
+ $0 = b;
+ } }$
+
+###### print binode cases
+ case Index:
+ print_exec(b->left, -1, 0);
+ printf("[");
+ print_exec(b->right, -1, 0);
+ printf("]");
+ break;
+
+###### propagate binode cases
+ case Index:
+ /* left must be an array, right must be a number,
+ * result is the member type of the array
+ */
+ propagate_types(b->right, c, ok, Tnum, 0);
+ t = propagate_types(b->left, c, ok, NULL, rules & Rnoconstant);
+ if (!t || t->compat != array_compat) {
+ type_err(c, "error: %1 cannot be indexed", prog, t, 0, NULL);
+ *ok = 0;
+ return NULL;
+ } else {
+ if (!type_compat(type, t->array.member, rules)) {
+ type_err(c, "error: have %1 but need %2", prog,
+ t->array.member, rules, type);
+ *ok = 0;
+ }
+ return t->array.member;
+ }
+ break;
+
+###### interp binode cases
+ case Index: {
+ mpz_t q;
+ long i;
+
+ lleft = linterp_exec(b->left);
+ right = interp_exec(b->right);
+ mpz_init(q);
+ mpz_tdiv_q(q, mpq_numref(right.num), mpq_denref(right.num));
+ i = mpz_get_si(q);
+ mpz_clear(q);
+
+ if (i >= 0 && i < lleft->type->array.size)
+ lrv = &lleft->array.elmnts[i];
+ else
+ rv = val_init(lleft->type->array.member);
+ break;
}
## Language elements
### Values
We have already met values as separate objects. When manifest
-constants appear in the program text that must result in an executable
+constants appear in the program text, that must result in an executable
which has a constant value. So the `val` structure embeds a value in
an executable.
$*val
Value -> True ${
$0 = new_pos(val, $1);
- $0->val.vtype = Vbool;
+ $0->val.type = Tbool;
$0->val.bool = 1;
}$
| False ${
$0 = new_pos(val, $1);
- $0->val.vtype = Vbool;
+ $0->val.type = Tbool;
$0->val.bool = 0;
}$
| NUMBER ${
$0 = new_pos(val, $1);
- $0->val.vtype = Vnum;
- if (number_parse($0->val.num, $0->val.tail, $1.txt) == 0)
+ $0->val.type = Tnum;
+ {
+ char tail[3];
+ if (number_parse($0->val.num, tail, $1.txt) == 0)
mpq_init($0->val.num);
+ if (tail[0])
+ tok_err(config2context(config), "error: unsupported number suffix",
+ &$1);
+ }
}$
| STRING ${
$0 = new_pos(val, $1);
- $0->val.vtype = Vstr;
- string_parse(&$1, '\\', &$0->val.str, $0->val.tail);
+ $0->val.type = Tstr;
+ {
+ char tail[3];
+ string_parse(&$1, '\\', &$0->val.str, tail);
+ if (tail[0])
+ tok_err(config2context(config), "error: unsupported string suffix",
+ &$1);
+ }
}$
| MULTI_STRING ${
$0 = new_pos(val, $1);
- $0->val.vtype = Vstr;
- string_parse(&$1, '\\', &$0->val.str, $0->val.tail);
+ $0->val.type = Tstr;
+ {
+ char tail[3];
+ string_parse(&$1, '\\', &$0->val.str, tail);
+ if (tail[0])
+ tok_err(config2context(config), "error: unsupported string suffix",
+ &$1);
+ }
}$
###### print exec cases
case Xval:
{
struct val *v = cast(val, e);
- if (v->val.vtype == Vstr)
+ if (v->val.type == Tstr)
printf("\"");
print_value(v->val);
- if (v->val.vtype == Vstr)
+ if (v->val.type == Tstr)
printf("\"");
break;
}
case Xval:
{
struct val *val = cast(val, prog);
- if (!vtype_compat(type, val->val.vtype, bool_permitted)) {
- type_err(c, "error: expected %1 found %2",
- prog, type, val->val.vtype);
+ if (!type_compat(type, val->val.type, rules)) {
+ type_err(c, "error: expected %1%r found %2",
+ prog, type, rules, val->val.type);
*ok = 0;
}
- return val->val.vtype;
+ return val->val.type;
}
###### interp exec cases
case Xval:
- return dup_value(cast(val, e)->val);
+ rv = dup_value(cast(val, e)->val);
+ break;
###### ast functions
static void free_val(struct val *v)
### Variables
-Just as we used as `val` to wrap a value into an `exec`, we similarly
+Just as we used a `val` to wrap a value into an `exec`, we similarly
need a `var` to wrap a `variable` into an exec. While each `val`
contained a copy of the value, each `var` hold a link to the variable
because it really is the same variable no matter where it appears.
###### Grammar
$*var
- VariableDecl -> IDENTIFIER := ${ {
+ VariableDecl -> IDENTIFIER : ${ {
struct variable *v = var_decl(config2context(config), $1.txt);
$0 = new_pos(var, $1);
$0->var = v;
v = var_ref(config2context(config), $1.txt);
$0->var = v;
type_err(config2context(config), "error: variable '%v' redeclared",
- $0, Vnone, Vnone);
+ $0, Tnone, 0, Tnone);
type_err(config2context(config), "info: this is where '%v' was first declared",
- v->where_decl, Vnone, Vnone);
+ v->where_decl, Tnone, 0, Tnone);
}
} }$
- | IDENTIFIER ::= ${ {
+ | IDENTIFIER :: ${ {
struct variable *v = var_decl(config2context(config), $1.txt);
$0 = new_pos(var, $1);
$0->var = v;
v = var_ref(config2context(config), $1.txt);
$0->var = v;
type_err(config2context(config), "error: variable '%v' redeclared",
- $0, Vnone, Vnone);
+ $0, Tnone, 0, Tnone);
type_err(config2context(config), "info: this is where '%v' was first declared",
- v->where_decl, Vnone, Vnone);
+ v->where_decl, Tnone, 0, Tnone);
+ }
+ } }$
+ | IDENTIFIER : Type ${ {
+ struct variable *v = var_decl(config2context(config), $1.txt);
+ $0 = new_pos(var, $1);
+ $0->var = v;
+ if (v) {
+ v->where_decl = $0;
+ v->where_set = $0;
+ v->val = val_prepare($<3);
+ } else {
+ v = var_ref(config2context(config), $1.txt);
+ $0->var = v;
+ type_err(config2context(config), "error: variable '%v' redeclared",
+ $0, Tnone, 0, Tnone);
+ type_err(config2context(config), "info: this is where '%v' was first declared",
+ v->where_decl, Tnone, 0, Tnone);
+ }
+ } }$
+ | IDENTIFIER :: Type ${ {
+ struct variable *v = var_decl(config2context(config), $1.txt);
+ $0 = new_pos(var, $1);
+ $0->var = v;
+ if (v) {
+ v->where_decl = $0;
+ v->where_set = $0;
+ v->val = val_prepare($<3);
+ v->constant = 1;
+ } else {
+ v = var_ref(config2context(config), $1.txt);
+ $0->var = v;
+ type_err(config2context(config), "error: variable '%v' redeclared",
+ $0, Tnone, 0, Tnone);
+ type_err(config2context(config), "info: this is where '%v' was first declared",
+ v->where_decl, Tnone, 0, Tnone);
}
} }$
+ $*exec
Variable -> IDENTIFIER ${ {
struct variable *v = var_ref(config2context(config), $1.txt);
$0 = new_pos(var, $1);
/* This might be a label - allocate a var just in case */
v = var_decl(config2context(config), $1.txt);
if (v) {
- val_init(&v->val, Vlabel);
+ v->val = val_prepare(Tlabel);
+ v->val.label = &v->val;
v->where_set = $0;
}
}
- $0->var = v;
+ cast(var, $0)->var = v;
} }$
+ ## variable grammar
+
+ $*type
+ Type -> IDENTIFIER ${
+ $0 = find_type(config2context(config), $1.txt);
+ if (!$0) {
+ tok_err(config2context(config),
+ "error: undefined type", &$1);
+
+ $0 = Tnone;
+ }
+ }$
+ ## type grammar
###### print exec cases
case Xvar:
struct binding *b = v->var->name;
fprintf(stderr, "%.*s", b->name.len, b->name.txt);
} else
- fputs("???", stderr);
+ fputs("???", stderr); // NOTEST
} else
- fputs("NOTVAR", stderr);
+ fputs("NOTVAR", stderr); // NOTEST
break;
###### propagate exec cases
struct var *var = cast(var, prog);
struct variable *v = var->var;
if (!v) {
- type_err(c, "%d:BUG: no variable!!", prog, Vnone, Vnone);
- *ok = 0;
- return Vnone;
+ type_err(c, "%d:BUG: no variable!!", prog, Tnone, 0, Tnone); // NOTEST
+ *ok = 0; // NOTEST
+ return Tnone; // NOTEST
}
if (v->merged)
v = v->merged;
- if (v->val.vtype == Vunknown) {
- if (type > Vunknown && *ok != 0) {
- val_init(&v->val, type);
+ if (v->constant && (rules & Rnoconstant)) {
+ type_err(c, "error: Cannot assign to a constant: %v",
+ prog, NULL, 0, NULL);
+ type_err(c, "info: name was defined as a constant here",
+ v->where_decl, NULL, 0, NULL);
+ *ok = 0;
+ return v->val.type;
+ }
+ if (v->val.type == NULL) {
+ if (type && *ok != 0) {
+ v->val = val_prepare(type);
v->where_set = prog;
*ok = 2;
}
return type;
}
- if (!vtype_compat(type, v->val.vtype, bool_permitted)) {
- type_err(c, "error: expected %1 but variable '%v' is %2", prog,
- type, v->val.vtype);
+ if (!type_compat(type, v->val.type, rules)) {
+ type_err(c, "error: expected %1%r but variable '%v' is %2", prog,
+ type, rules, v->val.type);
type_err(c, "info: this is where '%v' was set to %1", v->where_set,
- v->val.vtype, Vnone);
+ v->val.type, rules, Tnone);
*ok = 0;
}
- if (type <= Vunknown)
- return v->val.vtype;
+ if (!type)
+ return v->val.type;
return type;
}
if (v->merged)
v = v->merged;
- return dup_value(v->val);
+ lrv = &v->val;
+ break;
}
###### ast functions
###### free exec cases
case Xvar: free_var(cast(var, e)); break;
+### Expressions: Conditional
+
+Our first user of the `binode` will be conditional expressions, which
+is a bit odd as they actually have three components. That will be
+handled by having 2 binodes for each expression. The conditional
+expression is the lowest precedence operatior, so it gets to define
+what an "Expression" is. The next level up is "BoolExpr", which
+comes next.
+
+Conditional expressions are of the form "value `if` condition `else`
+other_value". There is no associativite with this operator: the
+values and conditions can only be other conditional expressions if
+they are enclosed in parentheses. Allowing nesting without
+parentheses would be too confusing.
+
+###### Binode types
+ CondExpr,
+
+###### Grammar
+
+ $*exec
+ Expression -> BoolExpr if BoolExpr else BoolExpr ${ {
+ struct binode *b1 = new(binode);
+ struct binode *b2 = new(binode);
+ b1->op = CondExpr;
+ b1->left = $<3;
+ b1->right = b2;
+ b2->op = CondExpr;
+ b2->left = $<1;
+ b2->right = $<5;
+ $0 = b1;
+ } }$
+ | BoolExpr ${ $0 = $<1; }$
+
+###### print binode cases
+
+ case CondExpr:
+ b2 = cast(binode, b->right);
+ print_exec(b2->left, -1, 0);
+ printf(" if ");
+ print_exec(b->left, -1, 0);
+ printf(" else ");
+ print_exec(b2->right, -1, 0);
+ break;
+
+###### propagate binode cases
+
+ case CondExpr: {
+ /* cond must be Tbool, others must match */
+ struct binode *b2 = cast(binode, b->right);
+ struct type *t2;
+
+ propagate_types(b->left, c, ok, Tbool, 0);
+ t = propagate_types(b2->left, c, ok, type, Rnolabel);
+ t2 = propagate_types(b2->right, c, ok, type ?: t, Rnolabel);
+ return t ?: t2;
+ }
+
+###### interp binode cases
+
+ case CondExpr: {
+ struct binode *b2 = cast(binode, b->right);
+ left = interp_exec(b->left);
+ if (left.bool)
+ rv = interp_exec(b2->left);
+ else
+ rv = interp_exec(b2->right);
+ }
+ break;
+
### Expressions: Boolean
-Our first user of the `binode` will be expressions, and particularly
-Boolean expressions. As I haven't implemented precedence in the
-parser generator yet, we need different names from each precedence
-level used by expressions. The outer most or lowest level precedence
-are Boolean `or` `and`, and `not` which form an `Expression` out of `BTerm`s
-and `BFact`s.
+The next class of expressions to use the `binode` will be Boolean
+expressions. As I haven't implemented precedence in the parser
+generator yet, we need different names for each precedence level used
+by expressions. The outer most or lowest level precedence are
+conditional expressions are Boolean operators which form an `BoolExpr`
+out of `BTerm`s and `BFact`s. As well as `or` `and`, and `not` we
+have `and then` and `or else` which only evaluate the second operand
+if the result would make a difference.
###### Binode types
And,
+ AndThen,
Or,
+ OrElse,
Not,
-####### Grammar
+###### Grammar
$*exec
- Expression -> Expression or BTerm ${ {
+ BoolExpr -> BoolExpr or BTerm ${ {
struct binode *b = new(binode);
b->op = Or;
b->left = $<1;
b->right = $<3;
$0 = b;
} }$
+ | BoolExpr or else BTerm ${ {
+ struct binode *b = new(binode);
+ b->op = OrElse;
+ b->left = $<1;
+ b->right = $<4;
+ $0 = b;
+ } }$
| BTerm ${ $0 = $<1; }$
BTerm -> BTerm and BFact ${ {
b->right = $<3;
$0 = b;
} }$
+ | BTerm and then BFact ${ {
+ struct binode *b = new(binode);
+ b->op = AndThen;
+ b->left = $<1;
+ b->right = $<4;
+ $0 = b;
+ } }$
| BFact ${ $0 = $<1; }$
BFact -> not BFact ${ {
printf(" and ");
print_exec(b->right, -1, 0);
break;
+ case AndThen:
+ print_exec(b->left, -1, 0);
+ printf(" and then ");
+ print_exec(b->right, -1, 0);
+ break;
case Or:
print_exec(b->left, -1, 0);
printf(" or ");
print_exec(b->right, -1, 0);
break;
+ case OrElse:
+ print_exec(b->left, -1, 0);
+ printf(" or else ");
+ print_exec(b->right, -1, 0);
+ break;
case Not:
printf("not ");
print_exec(b->right, -1, 0);
###### propagate binode cases
case And:
+ case AndThen:
case Or:
+ case OrElse:
case Not:
- /* both must be Vbool, result is Vbool */
- propagate_types(b->left, c, ok, Vbool, 0);
- propagate_types(b->right, c, ok, Vbool, 0);
- if (type != Vbool && type > Vunknown) {
+ /* both must be Tbool, result is Tbool */
+ propagate_types(b->left, c, ok, Tbool, 0);
+ propagate_types(b->right, c, ok, Tbool, 0);
+ if (type && type != Tbool) {
type_err(c, "error: %1 operation found where %2 expected", prog,
- Vbool, type);
+ Tbool, 0, type);
*ok = 0;
}
- return Vbool;
+ return Tbool;
###### interp binode cases
case And:
right = interp_exec(b->right);
rv.bool = rv.bool && right.bool;
break;
+ case AndThen:
+ rv = interp_exec(b->left);
+ if (rv.bool)
+ rv = interp_exec(b->right);
+ break;
case Or:
rv = interp_exec(b->left);
right = interp_exec(b->right);
rv.bool = rv.bool || right.bool;
break;
+ case OrElse:
+ rv = interp_exec(b->left);
+ if (!rv.bool)
+ rv = interp_exec(b->right);
+ break;
case Not:
rv = interp_exec(b->right);
rv.bool = !rv.bool;
A comparison takes arguments of any type, but the two types must be
the same.
-To simplify the parsing we introduce an `eop` which can return an
+To simplify the parsing we introduce an `eop` which can record an
expression operator.
###### ast
case GtrEq: printf(" >= "); break;
case Eql: printf(" == "); break;
case NEql: printf(" != "); break;
- default: abort();
+ default: abort(); // NOTEST
}
print_exec(b->right, -1, 0);
break;
case GtrEq:
case Eql:
case NEql:
- /* Both must match but not labels, result is Vbool */
- t = propagate_types(b->left, c, ok, Vnolabel, 0);
- if (t > Vunknown)
+ /* Both must match but not be labels, result is Tbool */
+ t = propagate_types(b->left, c, ok, NULL, Rnolabel);
+ if (t)
propagate_types(b->right, c, ok, t, 0);
else {
- t = propagate_types(b->right, c, ok, Vnolabel, 0);
- if (t > Vunknown)
+ t = propagate_types(b->right, c, ok, NULL, Rnolabel);
+ if (t)
t = propagate_types(b->left, c, ok, t, 0);
}
- if (!vtype_compat(type, Vbool, 0)) {
+ if (!type_compat(type, Tbool, 0)) {
type_err(c, "error: Comparison returns %1 but %2 expected", prog,
- Vbool, type);
+ Tbool, rules, type);
*ok = 0;
}
- return Vbool;
+ return Tbool;
###### interp binode cases
case Less:
left = interp_exec(b->left);
right = interp_exec(b->right);
cmp = value_cmp(left, right);
- rv.vtype = Vbool;
+ rv.type = Tbool;
switch (b->op) {
case Less: rv.bool = cmp < 0; break;
case LessEq: rv.bool = cmp <= 0; break;
case GtrEq: rv.bool = cmp >= 0; break;
case Eql: rv.bool = cmp == 0; break;
case NEql: rv.bool = cmp != 0; break;
- default: rv.bool = 0; break;
+ default: rv.bool = 0; break; // NOTEST
}
break;
}
### Expressions: The rest
The remaining expressions with the highest precedence are arithmetic
-and string concatenation. There are `Expr`, `Term`, and `Factor`.
+and string concatenation. They are `Expr`, `Term`, and `Factor`.
The `Factor` is where the `Value` and `Variable` that we already have
are included.
absolute value and negation). These have different operator names.
We also have a 'Bracket' operator which records where parentheses were
-found. This make it easy to reproduce these when printing. Once
+found. This makes it easy to reproduce these when printing. Once
precedence is handled better I might be able to discard this.
###### Binode types
Plus, Minus,
- Times, Divide,
+ Times, Divide, Rem,
Concat,
Absolute, Negate,
Bracket,
Top -> * ${ $0.op = Times; }$
| / ${ $0.op = Divide; }$
+ | % ${ $0.op = Rem; }$
| ++ ${ $0.op = Concat; }$
###### print binode cases
case Times:
case Divide:
case Concat:
+ case Rem:
print_exec(b->left, indent, 0);
switch(b->op) {
- case Plus: printf(" + "); break;
- case Minus: printf(" - "); break;
- case Times: printf(" * "); break;
- case Divide: printf(" / "); break;
- case Concat: printf(" ++ "); break;
- default: abort();
- }
+ case Plus: fputs(" + ", stdout); break;
+ case Minus: fputs(" - ", stdout); break;
+ case Times: fputs(" * ", stdout); break;
+ case Divide: fputs(" / ", stdout); break;
+ case Rem: fputs(" % ", stdout); break;
+ case Concat: fputs(" ++ ", stdout); break;
+ default: abort(); // NOTEST
+ } // NOTEST
print_exec(b->right, indent, 0);
break;
case Absolute:
case Plus:
case Minus:
case Times:
+ case Rem:
case Divide:
- /* both must be numbers, result is Vnum */
+ /* both must be numbers, result is Tnum */
case Absolute:
case Negate:
/* as propagate_types ignores a NULL,
* unary ops fit here too */
- propagate_types(b->left, c, ok, Vnum, 0);
- propagate_types(b->right, c, ok, Vnum, 0);
- if (!vtype_compat(type, Vnum, 0)) {
+ propagate_types(b->left, c, ok, Tnum, 0);
+ propagate_types(b->right, c, ok, Tnum, 0);
+ if (!type_compat(type, Tnum, 0)) {
type_err(c, "error: Arithmetic returns %1 but %2 expected", prog,
- Vnum, type);
+ Tnum, rules, type);
*ok = 0;
}
- return Vnum;
+ return Tnum;
case Concat:
- /* both must be Vstr, result is Vstr */
- propagate_types(b->left, c, ok, Vstr, 0);
- propagate_types(b->right, c, ok, Vstr, 0);
- if (!vtype_compat(type, Vstr, 0)) {
+ /* both must be Tstr, result is Tstr */
+ propagate_types(b->left, c, ok, Tstr, 0);
+ propagate_types(b->right, c, ok, Tstr, 0);
+ if (!type_compat(type, Tstr, 0)) {
type_err(c, "error: Concat returns %1 but %2 expected", prog,
- Vstr, type);
+ Tstr, rules, type);
*ok = 0;
}
- return Vstr;
+ return Tstr;
case Bracket:
return propagate_types(b->right, c, ok, type, 0);
right = interp_exec(b->right);
mpq_div(rv.num, rv.num, right.num);
break;
+ case Rem: {
+ mpz_t l, r, rem;
+
+ left = interp_exec(b->left);
+ right = interp_exec(b->right);
+ mpz_init(l); mpz_init(r); mpz_init(rem);
+ mpz_tdiv_q(l, mpq_numref(left.num), mpq_denref(left.num));
+ mpz_tdiv_q(r, mpq_numref(right.num), mpq_denref(right.num));
+ mpz_tdiv_r(rem, l, r);
+ rv = val_init(Tnum);
+ mpq_set_z(rv.num, rem);
+ mpz_clear(r); mpz_clear(l); mpz_clear(rem);
+ break;
+ }
case Negate:
rv = interp_exec(b->right);
mpq_neg(rv.num, rv.num);
case Concat:
left = interp_exec(b->left);
right = interp_exec(b->right);
- rv.vtype = Vstr;
+ rv.type = Tstr;
rv.str = text_join(left.str, right.str);
break;
+
+###### value functions
+
+ static struct text text_join(struct text a, struct text b)
+ {
+ struct text rv;
+ rv.len = a.len + b.len;
+ rv.txt = malloc(rv.len);
+ memcpy(rv.txt, a.txt, a.len);
+ memcpy(rv.txt+a.len, b.txt, b.len);
+ return rv;
+ }
+
+
### Blocks, Statements, and Statement lists.
Now that we have expressions out of the way we need to turn to
The later comprise complex statements and simple statement lists. They are
separated by newlines. Thus the semicolon is only used to separate
simple statements on the one line. This may be overly restrictive,
-but I'm not sure I every want a complex statement to share a line with
+but I'm not sure I ever want a complex statement to share a line with
anything else.
Note that a simple statement list can still use multiple lines if
The only stand-alone statement we introduce at this stage is `pass`
which does nothing and is represented as a `NULL` pointer in a `Block`
-list.
+list. Other stand-alone statements will follow once the infrastructure
+is in-place.
###### Binode types
Block,
###### propagate binode cases
case Block:
{
- /* If any statement returns something other then Vnone
- * or Vbool then all such must return same type.
- * As each statement may be Vnone or something else,
- * we must always pass Vunknown down, otherwise an incorrect
- * error might occur. We never return Vnone unless it is
+ /* If any statement returns something other than Tnone
+ * or Tbool then all such must return same type.
+ * As each statement may be Tnone or something else,
+ * we must always pass NULL (unknown) down, otherwise an incorrect
+ * error might occur. We never return Tnone unless it is
* passed in.
*/
struct binode *e;
for (e = b; e; e = cast(binode, e->right)) {
- t = propagate_types(e->left, c, ok, Vunknown, bool_permitted);
- if (bool_permitted && t == Vbool)
- t = Vunknown;
- if (t != Vunknown && t != Vnone && t != Vbool) {
- if (type == Vunknown)
+ t = propagate_types(e->left, c, ok, NULL, rules);
+ if ((rules & Rboolok) && t == Tbool)
+ t = NULL;
+ if (t && t != Tnone && t != Tbool) {
+ if (!type)
type = t;
else if (t != type) {
- type_err(c, "error: expected %1, found %2",
- e->left, type, t);
+ type_err(c, "error: expected %1%r, found %2",
+ e->left, type, rules, t);
*ok = 0;
}
}
###### interp binode cases
case Block:
- while (rv.vtype == Vnone &&
+ while (rv.type == Tnone &&
b) {
if (b->left)
rv = interp_exec(b->left);
case Print:
/* don't care but all must be consistent */
- propagate_types(b->left, c, ok, Vnolabel, 0);
- propagate_types(b->right, c, ok, Vnolabel, 0);
+ propagate_types(b->left, c, ok, NULL, Rnolabel);
+ propagate_types(b->right, c, ok, NULL, Rnolabel);
break;
###### interp binode cases
sep = ' ';
} else if (sep)
eol = 0;
- left.vtype = Vnone;
+ left.type = Tnone;
if (eol)
printf("\n");
break;
calculation. There is a form of assignment which declares a new
variable as well as assigning a value. If a name is assigned before
it is declared, and error will be raised as the name is created as
-`Vlabel` and it is illegal to assign to such names.
+`Tlabel` and it is illegal to assign to such names.
###### Binode types
Assign,
Declare,
###### SimpleStatement Grammar
- | Variable = Expression ${ {
- struct var *v = cast(var, $1);
-
+ | Variable = Expression ${
$0 = new(binode);
$0->op = Assign;
$0->left = $<1;
$0->right = $<3;
- if (v->var && !v->var->constant) {
- /* FIXME error? */
- }
- } }$
- | VariableDecl Expression ${
+ }$
+ | VariableDecl = Expression ${
$0 = new(binode);
$0->op = Declare;
$0->left = $<1;
- $0->right =$<2;
+ $0->right =$<3;
+ }$
+
+ | VariableDecl ${
+ if ($1->var->where_set == NULL) {
+ type_err(config2context(config), "Variable declared with no type or value: %v",
+ $1, NULL, 0, NULL);
+ } else {
+ $0 = new(binode);
+ $0->op = Declare;
+ $0->left = $<1;
+ $0->right = NULL;
+ }
}$
###### print binode cases
break;
case Declare:
+ {
+ struct variable *v = cast(var, b->left)->var;
do_indent(indent, "");
print_exec(b->left, indent, 0);
- if (cast(var, b->left)->var->constant)
- printf(" ::= ");
- else
- printf(" := ");
- print_exec(b->right, indent, 0);
+ if (cast(var, b->left)->var->constant) {
+ if (v->where_decl == v->where_set) {
+ printf("::");
+ type_print(v->val.type, stdout);
+ printf(" ");
+ } else
+ printf(" ::");
+ } else {
+ if (v->where_decl == v->where_set) {
+ printf(":");
+ type_print(v->val.type, stdout);
+ printf(" ");
+ } else
+ printf(" :");
+ }
+ if (b->right) {
+ printf("= ");
+ print_exec(b->right, indent, 0);
+ }
if (indent >= 0)
printf("\n");
+ }
break;
###### propagate binode cases
case Assign:
case Declare:
- /* Both must match and not be labels, result is Vnone */
- t = propagate_types(b->left, c, ok, Vnolabel, 0);
- if (t > Vunknown) {
+ /* Both must match and not be labels,
+ * Type must support 'dup',
+ * For Assign, left must not be constant.
+ * result is Tnone
+ */
+ t = propagate_types(b->left, c, ok, NULL,
+ Rnolabel | (b->op == Assign ? Rnoconstant : 0));
+ if (!b->right)
+ return Tnone;
+
+ if (t) {
if (propagate_types(b->right, c, ok, t, 0) != t)
if (b->left->type == Xvar)
type_err(c, "info: variable '%v' was set as %1 here.",
- cast(var, b->left)->var->where_set, t, Vnone);
+ cast(var, b->left)->var->where_set, t, rules, Tnone);
} else {
- t = propagate_types(b->right, c, ok, Vnolabel, 0);
- if (t > Vunknown)
- propagate_types(b->left, c, ok, t, 0);
+ t = propagate_types(b->right, c, ok, NULL, Rnolabel);
+ if (t)
+ propagate_types(b->left, c, ok, t,
+ (b->op == Assign ? Rnoconstant : 0));
}
- return Vnone;
+ if (t && t->dup == NULL) {
+ type_err(c, "error: cannot assign value of type %1", b, t, 0, NULL);
+ *ok = 0;
+ }
+ return Tnone;
break;
###### interp binode cases
case Assign:
+ lleft = linterp_exec(b->left);
+ right = interp_exec(b->right);
+ if (lleft) {
+ free_value(*lleft);
+ *lleft = right;
+ } else
+ free_value(right); // NOTEST
+ right.type = NULL;
+ break;
+
case Declare:
{
struct variable *v = cast(var, b->left)->var;
if (v->merged)
v = v->merged;
- right = interp_exec(b->right);
+ if (b->right)
+ right = interp_exec(b->right);
+ else
+ right = val_init(v->val.type);
free_value(v->val);
v->val = right;
- right.vtype = Vunknown;
+ right.type = NULL;
break;
}
subsumes `if`, `while`, `do/while`, `switch`, and some parts of `for`.
It is comprised of a number of parts, all of which are optional though
set combinations apply. Each part is (usually) a key word (`then` is
-sometimes optional) followed by either an expression of a code block,
+sometimes optional) followed by either an expression or a code block,
except the `casepart` which is a "key word and an expression" followed
by a code block. The code-block option is valid for all parts and,
where an expression is also allowed, the code block can use the `use`
-statement to report a value. If the code block does no report a value
-the effect is similar to reporting `False`.
+statement to report a value. If the code block does not report a value
+the effect is similar to reporting `True`.
The `else` and `case` parts, as well as `then` when combined with
`if`, can contain a `use` statement which will apply to some
The type requirements on the code block in a `whilepart` are quite
unusal. It is allowed to return a value of some identifiable type, in
-which case the loop abort and an appropriate `casepart` is run, or it
+which case the loop aborts and an appropriate `casepart` is run, or it
can return a Boolean, in which case the loop either continues to the
`dopart` (on `True`) or aborts and runs the `elsepart` (on `False`).
This is different both from the `ifpart` code block which is expected to
return a Boolean, or the `switchpart` code block which is expected to
return the same type as the casepart values. The correct analysis of
the type of the `whilepart` code block is the reason for the
-`bool_permitted` flag which is passed to `propagate_types()`.
+`Rboolok` flag which is passed to `propagate_types()`.
The `cond_statement` cannot fit into a `binode` so a new `exec` is
defined.
###### propagate exec cases
case Xcond_statement:
{
- // forpart and dopart must return Vnone
- // thenpart must return Vnone if there is a dopart,
+ // forpart and dopart must return Tnone
+ // thenpart must return Tnone if there is a dopart,
// otherwise it is like elsepart.
// condpart must:
- // be bool if there is not casepart
+ // be bool if there is no casepart
// match casepart->values if there is a switchpart
// either be bool or match casepart->value if there
// is a whilepart
- // elsepart, casepart->action must match there return type
- // expected of this statement.
+ // elsepart and casepart->action must match the return type
+ // expected of this statement.
struct cond_statement *cs = cast(cond_statement, prog);
struct casepart *cp;
- t = propagate_types(cs->forpart, c, ok, Vnone, 0);
- if (!vtype_compat(Vnone, t, 0))
+ t = propagate_types(cs->forpart, c, ok, Tnone, 0);
+ if (!type_compat(Tnone, t, 0))
*ok = 0;
- t = propagate_types(cs->dopart, c, ok, Vnone, 0);
- if (!vtype_compat(Vnone, t, 0))
+ t = propagate_types(cs->dopart, c, ok, Tnone, 0);
+ if (!type_compat(Tnone, t, 0))
*ok = 0;
if (cs->dopart) {
- t = propagate_types(cs->thenpart, c, ok, Vnone, 0);
- if (!vtype_compat(Vnone, t, 0))
+ t = propagate_types(cs->thenpart, c, ok, Tnone, 0);
+ if (!type_compat(Tnone, t, 0))
*ok = 0;
}
if (cs->casepart == NULL)
- propagate_types(cs->condpart, c, ok, Vbool, 0);
+ propagate_types(cs->condpart, c, ok, Tbool, 0);
else {
/* Condpart must match case values, with bool permitted */
- t = Vunknown;
+ t = NULL;
for (cp = cs->casepart;
- cp && (t == Vunknown); cp = cp->next)
- t = propagate_types(cp->value, c, ok, Vunknown, 0);
- if (t == Vunknown && cs->condpart)
- t = propagate_types(cs->condpart, c, ok, Vunknown, 1);
+ cp && !t; cp = cp->next)
+ t = propagate_types(cp->value, c, ok, NULL, 0);
+ if (!t && cs->condpart)
+ t = propagate_types(cs->condpart, c, ok, NULL, Rboolok);
// Now we have a type (I hope) push it down
- if (t != Vunknown) {
+ if (t) {
for (cp = cs->casepart; cp; cp = cp->next)
propagate_types(cp->value, c, ok, t, 0);
- propagate_types(cs->condpart, c, ok, t, 1);
+ propagate_types(cs->condpart, c, ok, t, Rboolok);
}
}
// (if)then, else, and case parts must return expected type.
- if (!cs->dopart && type == Vunknown)
- type = propagate_types(cs->thenpart, c, ok, Vunknown, bool_permitted);
- if (type == Vunknown)
- type = propagate_types(cs->elsepart, c, ok, Vunknown, bool_permitted);
+ if (!cs->dopart && !type)
+ type = propagate_types(cs->thenpart, c, ok, NULL, rules);
+ if (!type)
+ type = propagate_types(cs->elsepart, c, ok, NULL, rules);
for (cp = cs->casepart;
- cp && type == Vunknown;
+ cp && !type;
cp = cp->next)
- type = propagate_types(cp->action, c, ok, Vunknown, bool_permitted);
- if (type > Vunknown) {
+ type = propagate_types(cp->action, c, ok, NULL, rules);
+ if (type) {
if (!cs->dopart)
- propagate_types(cs->thenpart, c, ok, type, bool_permitted);
- propagate_types(cs->elsepart, c, ok, type, bool_permitted);
+ propagate_types(cs->thenpart, c, ok, type, rules);
+ propagate_types(cs->elsepart, c, ok, type, rules);
for (cp = cs->casepart; cp ; cp = cp->next)
- propagate_types(cp->action, c, ok, type, bool_permitted);
+ propagate_types(cp->action, c, ok, type, rules);
return type;
} else
- return Vunknown;
+ return NULL;
}
###### interp exec cases
struct value v, cnd;
struct casepart *cp;
struct cond_statement *c = cast(cond_statement, e);
+
if (c->forpart)
interp_exec(c->forpart);
do {
if (c->condpart)
cnd = interp_exec(c->condpart);
else
- cnd.vtype = Vnone;
- if (!(cnd.vtype == Vnone ||
- (cnd.vtype == Vbool && cnd.bool != 0)))
+ cnd.type = Tnone;
+ if (!(cnd.type == Tnone ||
+ (cnd.type == Tbool && cnd.bool != 0)))
break;
- if (c->dopart) {
- free_value(cnd);
+ // cnd is Tnone or Tbool, doesn't need to be freed
+ if (c->dopart)
interp_exec(c->dopart);
- }
+
if (c->thenpart) {
- v = interp_exec(c->thenpart);
- if (v.vtype != Vnone || !c->dopart)
- return v;
- free_value(v);
+ rv = interp_exec(c->thenpart);
+ if (rv.type != Tnone || !c->dopart)
+ goto Xcond_done;
+ free_value(rv);
}
} while (c->dopart);
if (value_cmp(v, cnd) == 0) {
free_value(v);
free_value(cnd);
- return interp_exec(cp->action);
+ rv = interp_exec(cp->action);
+ goto Xcond_done;
}
free_value(v);
}
free_value(cnd);
if (c->elsepart)
- return interp_exec(c->elsepart);
- v.vtype = Vnone;
- return v;
+ rv = interp_exec(c->elsepart);
+ else
+ rv.type = Tnone;
+ Xcond_done:
+ break;
}
+### Top level structure
+
+All the language elements so far can be used in various places. Now
+it is time to clarify what those places are.
+
+At the top level of a file there will be a number of declarations.
+Many of the things that can be declared haven't been described yet,
+such as functions, procedures, imports, named types, and probably
+more.
+For now there are two sorts of things that can appear at the top
+level. They are predefined constants and the main program. While the
+syntax will allow the main program to appear multiple times, that will
+trigger an error if it is actually attempted.
+
+The various declarations do not return anything. They store the
+various declarations in the parse context.
+
+###### Parser: grammar
+
+ $void
+ Ocean -> DeclarationList
+
+ DeclarationList -> Declaration
+ | DeclarationList Declaration
+
+ Declaration -> DeclareConstant
+ | DeclareProgram
+ | NEWLINE
+
+ ## top level grammar
+
+### The `const` section
+
+As well as being defined in with the code that uses them, constants
+can be declared at the top level. These have full-file scope, so they
+are always `InScope`. The value of a top level constant can be given
+as an expression, and this is evaluated immediately rather than in the
+later interpretation stage. Once we add functions to the language, we
+will need rules concern which, if any, can be used to define a top
+level constant.
+
+Constants are defined in a sectiont that starts with the reserved word
+`const` and then has a block with a list of assignment statements.
+For syntactic consistency, these must use the double-colon syntax to
+make it clear that they are constants. Type can also be given: if
+not, the type will be determined during analysis, as with other
+constants.
+
+###### top level grammar
+
+ DeclareConstant -> const Open ConstList Close
+ | const Open Newlines ConstList Close
+ | const Open SimpleConstList }
+ | const Open Newlines SimpleConstList }
+ | const : ConstList
+ | const SimpleConstList
+
+ ConstList -> ComplexConsts
+ ComplexConsts -> ComplexConst ComplexConsts
+ | ComplexConst
+ ComplexConst -> SimpleConstList NEWLINE
+ SimpleConstList -> Const ; SimpleConstList
+ | Const
+ | Const ; SimpleConstList ;
+
+ $*type
+ CType -> Type ${ $0 = $<1; }$
+ | ${ $0 = NULL; }$
+ $void
+ Const -> IDENTIFIER :: CType = Expression ${ {
+ int ok;
+ struct variable *v;
+
+ v = var_decl(config2context(config), $1.txt);
+ if (v) {
+ struct var *var = new_pos(var, $1);
+ v->where_decl = var;
+ v->where_set = var;
+ var->var = v;
+ v->constant = 1;
+ } else {
+ v = var_ref(config2context(config), $1.txt);
+ tok_err(config2context(config), "error: name already declared", &$1);
+ type_err(config2context(config), "info: this is where '%v' was first declared",
+ v->where_decl, NULL, 0, NULL);
+ }
+ do {
+ ok = 1;
+ propagate_types($5, config2context(config), &ok, $3, 0);
+ } while (ok == 2);
+ if (!ok)
+ config2context(config)->parse_error = 1;
+ else if (v) {
+ v->val = interp_exec($5);
+ }
+ } }$
+
+
### Finally the whole program.
Somewhat reminiscent of Pascal a (current) Ocean program starts with
the keyword "program" and a list of variable names which are assigned
values from command line arguments. Following this is a `block` which
-is the code to execute.
+is the code to execute. Unlike Pascal, constants and other
+declarations come *before* the program.
As this is the top level, several things are handled a bit
differently.
###### Binode types
Program,
-###### Parser: grammar
+###### top level grammar
+
+ DeclareProgram -> Program ${ {
+ struct parse_context *c = config2context(config);
+ if (c->prog)
+ type_err(c, "Program defined a second time",
+ $1, NULL, 0, NULL);
+ else
+ c->prog = $<1;
+ } }$
+
$*binode
Program -> program OpenScope Varlist Block OptNL ${
if (config2context(config)->scope_stack) abort();
}$
| ERROR ${
- fprintf(stderr, "%s:%d:%d: error: unhandled parse error.\n",
- config2context(config)->file_name, $1.line, $1.col);
- config2context(config)->parse_error = 1;
+ tok_err(config2context(config),
+ "error: unhandled parse error", &$1);
}$
Varlist -> Varlist ArgDecl ${
break;
###### propagate binode cases
- case Program: abort();
+ case Program: abort(); // NOTEST
###### core functions
int ok = 1;
if (!b)
- return 0;
+ return 0; // NOTEST
do {
ok = 1;
- propagate_types(b->right, c, &ok, Vnone, 0);
+ propagate_types(b->right, c, &ok, Tnone, 0);
} while (ok == 2);
if (!ok)
return 0;
for (b = cast(binode, b->left); b; b = cast(binode, b->right)) {
struct var *v = cast(var, b->left);
- if (v->var->val.vtype == Vunknown) {
+ if (!v->var->val.type) {
v->var->where_set = b;
- val_init(&v->var->val, Vstr);
+ v->var->val = val_prepare(Tstr);
}
}
b = cast(binode, prog);
do {
ok = 1;
- propagate_types(b->right, c, &ok, Vnone, 0);
+ propagate_types(b->right, c, &ok, Tnone, 0);
} while (ok == 2);
if (!ok)
return 0;
/* Make sure everything is still consistent */
- propagate_types(b->right, c, &ok, Vnone, 0);
+ propagate_types(b->right, c, &ok, Tnone, 0);
return !!ok;
}
struct value v;
if (!prog)
- return;
+ return; // NOTEST
al = cast(binode, p->left);
while (al) {
struct var *v = cast(var, al->left);
}
al = cast(binode, al->right);
free_value(*vl);
- if (!parse_value(vl, argv[0]))
+ *vl = parse_value(vl->type, argv[0]);
+ if (vl->type == NULL)
exit(1);
argv++;
}
}
###### interp binode cases
- case Program: abort();
+ case Program: abort(); // NOTEST
## And now to test it out.
###### test: hello
+ const:
+ pi ::= 3.1415926
+ four ::= 2 + 2 ; five ::= 10/2
+ const pie ::= "I like Pie";
+ cake ::= "The cake is"
+ ++ " a lie"
+
program A B:
print "Hello World, what lovely oceans you have!"
+ print "are there", five, "?"
+ print pi, pie, "but", cake
+
/* When a variable is defined in both branches of an 'if',
* and used afterwards, the variables are merged.
*/
/* If a variable is not used after the 'if', no
* merge happens, so types can be different
*/
- if A * 2 > B:
- double := "yes"
+ if A > B * 2:
+ double:string = "yes"
print A, "is more than twice", B, "?", double
else:
- double := A*2
- print "double", A, "is only", double
+ double := B*2
+ print "double", B, "is", double
- a := A; b := B
- if a > 0 and b > 0:
+ a : number
+ a = A;
+ b:number = B
+ if a > 0 and then b > 0:
while a != b:
if a < b:
b = b - a
print "Yay, I found", target
case GiveUp:
print "Closest I found was", mid
+
+ size::=55
+ list:[size]number
+ list[0] = 1234
+ for i:=1; then i = i + 1; while i < size:
+ n := list[i-1] * list[i-1]
+ list[i] = (n / 100) % 10000
+
+ print "Before sort:"
+ for i:=0; then i = i + 1; while i < size:
+ print "list[",i,"]=",list[i]
+
+ for i := 1; then i=i+1; while i < size:
+ for j:=i-1; then j=j-1; while j >= 0:
+ if list[j] > list[j+1]:
+ t:= list[j]
+ list[j] = list[j+1]
+ list[j+1] = t
+ print "After sort:"
+ for i:=0; then i = i + 1; while i < size:
+ print "list[",i,"]=",list[i]
code / ocean / blobdiff