2df43ef941
make data handling a little easier
2002-07-11 15:42:20 +00:00
1db26eea86
can't call pointer_type untill after the types are chained
2002-07-09 19:00:52 +00:00
2cb6138f2b
fix a silly segfault and make statement allocation saner
2002-07-08 20:31:59 +00:00
c1894db59f
split the emit stuf out of expr.h into emit.h
2002-07-08 18:53:07 +00:00
e815669b7a
finish (for now:/) qfo_to_progs
2002-07-08 16:13:06 +00:00
24e242ed35
move the type strings into their own string pool so the progs strings don't
...
get cluttered
2002-07-08 05:26:50 +00:00
598edb26fd
parse a type back from its encoding (some info will be lost)
2002-07-08 05:10:05 +00:00
c50923fa6f
expr_t forward declaration fix
2002-07-08 05:07:18 +00:00
4c8e157db2
nuke pr.statement_linenums as it was redundant and the info never used anyway
2002-07-08 03:05:44 +00:00
caf9d820c1
Forge updates. Forge now saves, but does not load (heh) projects.
2002-07-06 03:00:28 +00:00
5f54a1931b
fix an unused enum warning missed by gcc 3.0
2002-07-06 02:22:15 +00:00
5b98893003
bah, getting my "last changes vs last compile" backwards again :/
2002-07-05 20:19:13 +00:00
8a402381e6
redo how progs strings are stored so multiple pools can exist
2002-07-05 20:02:10 +00:00
576feacbf0
correct copyright year
2002-07-05 17:02:39 +00:00
7132e67f60
type encoding improvements
2002-07-05 16:59:25 +00:00
0ef4a7513d
d'oh, I thought I tested with those lines in :/
2002-07-03 21:38:14 +00:00
46bad45c7a
move s_file, pr_source_line and pr_error_count into pr, make the linker
...
errors more meaningful, and fix a blasted string.h issue (damn old gcc;P)
2002-07-03 21:32:03 +00:00
102eab0d84
linker.[ch]:
...
start working on the linker.
class.[ch]:
redo class defs so the pointer works (needs relocs still)
obj_file.h:
add prototype for read_obj_file, QFO_* data access macros and include
pr_debug.h
type.[ch]:
separate type system initialisation and recording of the standard types
so find_type works properly in multiple compilation
def.c:
don't mark static defs as initialized
expr.c:
proper class pointer def stuff
immediate.c:
clean out dead vars/code
obj_file.c:
allocate space for the line info and bail if the file can't be opened.
qfcc.c:
register the standard types for each compile pass and start linking the
files
2002-07-03 20:16:32 +00:00
9332ea30bc
oops, forgot to copy the string again when I went from strdup to save_string
2002-07-03 19:12:29 +00:00
b81f77803c
make extern more of a no-op when the def alread exists
2002-07-03 06:42:54 +00:00
4bd03bfff3
Hack to make error-on-warnings happy. *pokes taniwha*
2002-07-03 00:36:44 +00:00
211b11c8ae
some storage and obj file fixes
2002-07-02 23:08:44 +00:00
e6c4e0b576
some more storage class work
2002-07-02 21:34:40 +00:00
66aa36b73f
start implementing storage classes (extern, static, etc)
2002-06-28 17:59:32 +00:00
8e2dbc1947
gzwrite doesn't like 0 bytes
2002-06-28 16:52:41 +00:00
1a0b69e1d9
"qfcc *.qc" can now get through the prozac source withtout crashing (oodles
...
of compile errors, though:)
2002-06-28 16:38:05 +00:00
8415db2d84
clear out the hash tables for compiling multiple object files
2002-06-28 16:00:01 +00:00
536937b2e6
print out function param info
2002-06-27 22:51:42 +00:00
001571e25a
various memory saving tricks. seems to have not broken anything
2002-06-27 22:48:28 +00:00
be50d0e15a
sometimes, gcc 2.95 can be such a pain
2002-06-27 15:13:43 +00:00
0997d24dfd
the long time needed 3dfxstub.so
2002-06-27 05:42:58 +00:00
c963f300e6
Add include for string.h. Needs to be done more portably, but I'm too tired.
2002-06-26 23:01:25 +00:00
26dce371d9
clean up type allocation a little and also reloc allocation
2002-06-26 22:10:59 +00:00
362ec2a23a
do some freeing
2002-06-26 16:27:23 +00:00
78a626066e
get command line parsing working in an appropriate manner for separate
...
compilation
2002-06-25 21:36:10 +00:00
ecdb5a5cb4
allow the output file to be specified on the command line
2002-06-24 22:53:21 +00:00
4d496a2cd6
more endianess corrections and read/write line numbers
2002-06-24 22:36:04 +00:00
29d679154f
forgot to byteswap the code and data
2002-06-24 21:41:05 +00:00
f77bb44df3
load a qfo back into memory. next step is to figure out linking
2002-06-22 05:10:34 +00:00
9fee1d07dd
initial work on actually writing .qfo files. seems to work, but only test.qfo
...
is ever writtin :)
2002-06-21 20:46:56 +00:00
f8dee80355
add unions
2002-06-20 20:28:01 +00:00
f8e4215ba9
implement compiler "notices": potentially important information that isn't
...
really a warning (unless requested) and can be silenced.
2002-06-20 19:29:06 +00:00
3476138988
make --tradiontial cause "!foo & bar" evaluate as "!(foo & bar)" as per
...
qfcc's broken behaviour.
2002-06-20 18:51:46 +00:00
c8bc5dfb4c
QSG2 glows almost working. Plus lots of typos killed.
2002-06-18 21:41:24 +00:00
f90f78990a
ok, I'm happy with this now (bit fields anent' so great for portable file
...
formats:/)
2002-06-18 21:00:41 +00:00
8263d3bd85
start working on the format for the object files
2002-06-17 05:29:20 +00:00
37d3fecd5d
remove an unneeded field
2002-06-17 05:28:43 +00:00
cbffb4b140
clean up the vector def setup
2002-06-17 02:43:38 +00:00
b519c0b7cd
fix a silly typo that was causing the _y of vectors to get pointed to the
...
wrong place
2002-06-17 01:22:45 +00:00
2264c28310
pr_strings:
...
remove a bogus 0x which caused confusion in an error message
def.c:
vector fields still need an extra 3 globals for their component fields
2002-06-16 05:24:58 +00:00
e774943f24
va.[ch]:
...
new va function: nva which returns a strduped buffer
expr.c options.c:
use nva instead of strdup (va (...
struct.c type.c:
make type encoding work properly for structs
2002-06-13 16:39:33 +00:00
fb0318621d
and for my next amazing feat, I'll remove the debug code :P
2002-06-13 07:22:53 +00:00
5bbcbe0185
arrays seem to be working nicely now (menus work:)
2002-06-13 07:20:15 +00:00
71c9cdcc08
create pointer types correctly
2002-06-13 04:40:09 +00:00
88fc0be127
arrays are /almost/ working again
2002-06-12 22:37:18 +00:00
067c2dd6b2
globals.c:
...
don't crash on bad function numbers
qfprogs.c:
if the file doesn't load first try, thy appending .gz
2002-06-12 03:01:30 +00:00
0b1d1ade73
qfprogs can now read the debug data
2002-06-11 17:24:37 +00:00
afcda85a63
qfcc doc updates. lots more stuff.
2002-06-11 14:22:42 +00:00
331df31f6a
get the function number early so things don't get mixed up when new functions
...
get created while parsing a function
2002-06-11 06:54:32 +00:00
4932d0db3c
print the function number when printing the def
2002-06-11 06:51:29 +00:00
f7d8c2968f
better global (and other space) def re-use
2002-06-10 23:14:32 +00:00
1f67ea412d
add a global flag to def_t to make checking easier
...
rename pr.globals to pr.near_data and add pr.far_data
2002-06-10 20:54:22 +00:00
7a13e6b362
find the rest (I hope!) of the mis-tested scopes
2002-06-10 19:26:54 +00:00
a771beed74
qfcc.c:
...
def->scope is always non-0
qc-parse.y:
link defs from child scopes correctly
2002-06-10 19:07:32 +00:00
0747bcb099
set the debug function number correctly
2002-06-10 18:39:06 +00:00
98b601b91c
add the Objective-QC expressions
2002-06-10 16:10:44 +00:00
374d229a0e
more stuff
2002-06-10 06:18:59 +00:00
38c7505fe6
get a little further
2002-06-10 05:09:29 +00:00
a4142114ee
oh, no, not documentation!!! :)
2002-06-10 04:28:24 +00:00
42b1756e5e
rename qfcc.txt to qcc.txt as it's really more relevant to the old qcc
...
compiler, but still a good reference until the new docs are more advanced
2002-06-10 04:27:53 +00:00
e47570db69
must remember to test compile in the optimising tree :P
2002-06-09 16:34:50 +00:00
d0f76dfa13
dump function and field defs
2002-06-09 16:28:19 +00:00
58782333a9
give scopes types (static, params, locals for now)
2002-06-09 05:19:13 +00:00
1e57351be1
there, no more PR_* functions or pr_* files :)
2002-06-09 04:30:02 +00:00
943c2eefb3
redo def allocation to come from configurable `spaces' (locals, globals, far
...
globals, etc).
2002-06-09 03:57:20 +00:00
426dc07e53
fix a goof with the number of global defs
2002-06-09 03:41:11 +00:00
1cc91e9f10
add reloc.h
2002-06-08 21:12:14 +00:00
541f7ed1b8
some def stuff shuffling
2002-06-07 21:17:51 +00:00
0477b43f80
get rid of PR_GetArray: it's redundant
2002-06-07 18:14:39 +00:00
93169e1b91
rename two PR_* functions
2002-06-07 17:46:58 +00:00
dc0e31916f
fix a minor oopsie with the relocations
2002-06-07 17:39:57 +00:00
00a54ad918
redo relocations
2002-06-07 17:29:30 +00:00
8aa98c0d20
fix several silly mistakes
2002-06-06 21:51:47 +00:00
f31705380f
call malloc a little less often
2002-06-05 21:13:29 +00:00
38d3a15413
d'oh, forgot to compile test :P
2002-06-05 19:31:43 +00:00
cb395c5469
misc def improvments
2002-06-05 19:03:51 +00:00
9474765e75
remove some direct usages of pr.globals
2002-06-05 17:45:44 +00:00
e17604f9c2
remove all arbitrary limits except for globals. they'll need a little more
...
work. Once they're done, it should take quite a big mod to crash qfcc due
to too many strings/statements/etc :)
2002-06-05 17:12:55 +00:00
32215b1296
prepare functions and pr_globals for relocatability
2002-06-05 05:39:20 +00:00
935f1e8c5e
prepare the string hash table for relocatable strings space and fix a bug
...
causing more string space to be allocated than necessary
2002-06-05 05:24:42 +00:00
c58a4c59b7
forgot to move the prototypes
2002-06-04 21:54:47 +00:00
69605d0b19
even more cleanup
2002-06-04 21:23:39 +00:00
080a46469f
fix CPP_NAME for independently built qfcc
2002-06-04 20:43:11 +00:00
2d21e0e2fb
idstuff is a better name for precache
2002-06-04 18:45:45 +00:00
06bddd3ee6
more cleanup
2002-06-04 18:44:03 +00:00
77d244220b
more qfcc cleanup. split out some functions and kill some dead code
2002-06-04 05:25:37 +00:00
be28957dff
kill USE_CPP (and --enable-cpp) it's not needed any more
2002-06-04 04:48:21 +00:00
328b591aa0
some qfcc.c cleanup
2002-06-04 04:36:57 +00:00
e1d66fdfb8
make sure qc-parse.h gets built before files that depend on it
2002-06-03 03:45:24 +00:00
f00e892d4e
mingw gcc 3.1 is freaking weird
2002-06-02 05:27:32 +00:00
c13e94db78
must be more careful with the return value of va
2002-06-02 01:10:31 +00:00
84b46d720e
slowly killing cmdlib
2002-06-01 06:59:02 +00:00
8e479c5549
don't need that any more :)
2002-06-01 05:57:55 +00:00
12cfe6190b
do some file renaming
2002-06-01 05:37:18 +00:00
7b993f97d2
more cleanups
2002-06-01 05:30:16 +00:00
c4d0c574ee
clean up qfcc.h a bit
2002-06-01 05:06:19 +00:00
8f2d1fa2d9
more cmdlib cleanup
2002-06-01 04:41:25 +00:00
9e5f8c3bd9
win32 compile fixes
2002-05-31 19:24:56 +00:00
b3adadc347
@this will provide an id field named ".this" (ie, .id .this (if .this would
...
parse in the first place:))
also kill build_type now that a field_type function is available in type.c
2002-05-31 16:58:42 +00:00
4d267abd2a
make things a little quieter
2002-05-31 07:24:54 +00:00
3af96782da
make qwaq build as part of the main tree (but /not/ install)
2002-05-31 06:55:35 +00:00
96fe150ff4
Add a clean target to quaketoascii's makefile.
2002-05-31 06:44:48 +00:00
dd47617c57
Update some gitignore files.
2002-05-31 06:40:52 +00:00
c4811ccb52
seriously clean up qwaq. most of that stuff isn't needed any more
2002-05-31 06:16:10 +00:00
ce6854ad05
not everybody /has/ d.o :)
2002-05-31 06:09:08 +00:00
191232a383
get qwaq working with the objective stuff and do a simple messaging test
2002-05-31 06:02:26 +00:00
24e7a88719
fix some method list emission bugs
2002-05-31 06:00:11 +00:00
ccf2a0b34a
allocate defs using the correct size from the type
2002-05-31 05:04:16 +00:00
3c7fb6a312
fix some missing ;s
2002-05-30 21:18:58 +00:00
26cda3214a
Forge: partial support for projects. Very (VERY!) incomplete.
2002-05-29 11:21:25 +00:00
6c9c62139a
Forge updates: Windows are now remembered and stuff is in general a bit
...
cleaner. Committing this so that the stuff I'm about to write won't totally
fubar everything. :)
2002-05-29 07:13:42 +00:00
6fbf011073
rpm building fixes
2002-05-27 20:28:10 +00:00
3edc57ef93
Forge updates. Compiles with latest GNUstep CVS, may not work with current
...
release (but should).
The interface is no longer defined in code -- it loads it from a .gorm file.
The code is a lot cleaner, and I'm working on project management again.
Generally, I'm having a lot of fun. :)
2002-05-26 11:24:00 +00:00
a116529db1
pak tool: Re-add the -f option and clean up the man page.
2002-05-25 02:47:53 +00:00
34ec521198
vararg functions can now be imlemented in qc using @argc (number of params
...
passed through ...) and @argv (array of vectors, one for each ... param)
2002-05-22 20:43:29 +00:00
60457ee7b8
clean up some expr creaion
2002-05-22 17:18:48 +00:00
5b590c9301
that seems to have got the type parsing right. (void []) () foo will work
...
and .float () foo works too
2002-05-22 17:13:52 +00:00
ddcaef5b0b
that didn't work so well :/
...
back it out for now till I figure out how to get it parsing .float () foo
correctly
2002-05-22 16:38:29 +00:00
51fbbb7c5c
qc-parse.y:
...
allow complex types for function return values
type.c:
fix a missing break and an unneeded printout
2002-05-22 16:29:24 +00:00
3967f5cf95
type.h:
...
*type_method to type_Method
emit.c:
support casting between pointers
expr.c:
support casting between pointers
method.c:
correct the type for _cmd
type_method to type_Method.aux_type
qc-lex.l:
Method type is a poniter to a method
qc-parse.y:
support , args to messages (not fully implemented yet)
type.c:
*type_method to type_Method and make type_Method a pointer to a method
2002-05-22 05:03:36 +00:00
a1fe5efd27
initialize class_Class.super_class iff @keywords are seen (ie, compiling
...
obj code).
2002-05-22 01:39:07 +00:00
4697ce281e
define Protocol type correctly
2002-05-21 23:38:40 +00:00
4315707008
class.c:
...
avoid possible segfault
expr.c:
correct the return value type checking to handle super classes
2002-05-21 23:29:21 +00:00
3a99ab8cea
trim off the trailing _ from method def names
2002-05-21 23:02:56 +00:00
2a73235d35
fix some method bugs
2002-05-21 22:51:46 +00:00
9f06f89d57
write out the module data needed for the obj runtime
2002-05-21 21:28:40 +00:00
e11e2f3718
SELF -> @self (looks better (IMO:)) and make sure the .self def gets
...
generatoed and used when @self is seen
2002-05-18 00:30:14 +00:00
5be384da63
create a `SELF' keyword so the global self entity can be handled sanely.
...
Not fully implemented yet.
2002-05-17 20:25:46 +00:00
2c0de5cb3e
print out some extra info for function defs
2002-05-17 20:03:59 +00:00
dc5cd8460e
`super' is now a keyword
2002-05-17 19:47:15 +00:00
451bfbddfe
fix a snafu with current_class and get ivar access working properly (cross
...
fingers:)
2002-05-17 19:35:26 +00:00
d8c66aef76
don't seg if strct is null
2002-05-17 19:34:40 +00:00
2e8c18f8b6
handle unimplemented classes a little better (will do for now till I sort
...
out some sort of resolution for them)
2002-05-17 18:46:11 +00:00
b1d1159ae2
allow methods to be builtins
2002-05-17 18:35:54 +00:00
97170e97b5
setup the default visibility properly
2002-05-17 17:58:57 +00:00
ef9f9cda2f
pr_obj.h:
...
define the class info stuff
expr.h pr_def.c:
fix a FIXME
class.c expr.c type.c:
make id ev_pointer.ev_object rather than ev_pointer.ev_class
2002-05-17 17:37:44 +00:00
6965642030
get ivars working better (need to get rid of self.) and [super ...] now
...
works.
2002-05-17 06:20:27 +00:00
91c4039495
add some functionality to qfprogs (globals and strings dumping)
2002-05-16 23:44:53 +00:00
372c391737
initialize the string hash table with ""
2002-05-16 23:32:25 +00:00
04d76ce1cf
build the method_list struct with the correct type
2002-05-16 23:32:03 +00:00
7cdbef2b11
make class_def return a correct def
2002-05-16 22:33:11 +00:00
4908b3cf10
`initialize' the defs for the obj constructs
2002-05-16 21:57:03 +00:00
eba5e68726
check whether the method is an instance or class method when comparing
2002-05-16 20:48:41 +00:00
779174cb33
get object pointer assignmets working and some static typing as well
2002-05-16 20:20:23 +00:00
73f4cb4c03
it seems object info emition works (needs more testing)
2002-05-15 23:24:19 +00:00
308fa78fc6
lots of obj work
2002-05-15 19:10:23 +00:00
6a5bbf6f0a
memory allocation checking cleanup
2002-05-14 06:37:28 +00:00
44dcf74627
strip the \n from all(?) of the Sys_Error calls (Sys_Error itself will be
...
adding \n).
2002-05-14 06:12:29 +00:00
2c0a20a887
fix the mis-generation of code for state-functions
2002-05-13 20:11:33 +00:00
91779b04f7
new tool: qfprogs. currently only disassembles progs, but the idea is for it
...
to become a progs oriented nm, objdump etc
2002-05-13 19:37:36 +00:00
9b516ff84f
mild namespace cleanup
2002-05-11 03:37:36 +00:00
73e6cf062c
implement type encoding
2002-05-10 23:19:57 +00:00
b418701637
missing ;
2002-05-10 02:11:23 +00:00
2cd716176a
more progress
2002-05-10 00:00:23 +00:00
f2b8dc7e7e
more progress
2002-05-09 20:12:28 +00:00
55e54bd9f9
move the type and def externs to type.h
2002-05-09 17:11:14 +00:00
f4fee3d7b2
add id as a type
2002-05-09 06:37:40 +00:00
961d84e569
clean up of qfcc.h and shuffle around the predefined types
2002-05-09 06:34:48 +00:00
1b875c8b06
work on getting obj expressions going
2002-05-08 23:12:49 +00:00
7f47447492
getting closer to emiting ObjQC code
2002-05-08 21:24:24 +00:00
de86019d4b
reverse the param order before building the function type and type check
...
varargs functions with specified params.
2002-05-08 17:33:28 +00:00
b03bfa7a6e
start working on the code generation for the Obj stuff
2002-05-08 05:55:57 +00:00
b226d24b52
rework the param parsing to make selectors easier to handle
2002-05-08 05:15:19 +00:00
d5b637ae06
first stab at implementing ObjC like features. The parser doesn't generate
...
any code for the new features yet (I need to learn more about how objc
/works/) but nothing seems to have been broken.
2002-05-07 16:55:54 +00:00
cc0a428e2b
traking pak command line changes...
2002-05-07 03:47:01 +00:00
c164aa4ba5
Stomp out a warning.
2002-05-06 16:36:07 +00:00
4ce4869143
A better command-line interface for pak. NOTE: there has been a change in
...
how pak gets the filename for the archive. Instead of requiring an -f
argument, it now takes the first non-option argument as the filename. If
this is a problem, it can be changed back.
Also, a manual page.
2002-05-03 10:38:04 +00:00
74990f48ef
Testing it again. Closes : #35
2002-05-03 04:42:26 +00:00
536418a552
Testing my fix...
2002-05-03 04:41:53 +00:00
527c1bc5d1
testing. Closes : #35
2002-05-03 04:31:32 +00:00
2e2d2e2aa7
grr. Closes : #35
2002-05-03 04:25:33 +00:00
cd7f26ee0a
grr. Closes : #35
2002-05-03 04:14:28 +00:00
62148023f3
AGAIN. Closes : #35
2002-05-03 04:10:16 +00:00
9e2995997b
again. Closes: Bug#35
2002-05-03 04:07:06 +00:00
a6231fd977
one more time. Closes: Bug#35
2002-05-03 04:06:19 +00:00
6481b043e2
boo. Closes: 35
2002-05-03 04:00:53 +00:00
58dcd96966
?? (Closes: Bug#35)
2002-05-03 03:59:40 +00:00
c854369544
blah blah blah
2002-05-03 03:56:06 +00:00
4bacf36bf3
grr. Closes : #35
2002-05-03 03:49:44 +00:00
4423e6fbb7
One more time... Closes : #35
2002-05-03 03:48:28 +00:00
a47997bee7
Okay, this'd better work. Closes : #35
2002-05-03 03:46:38 +00:00
30f359f5c3
testing AGAIN. Closes: Bug#35
2002-05-03 03:39:49 +00:00
6d8cb67c18
testing again. Closes: Bug#35
2002-05-03 03:33:54 +00:00
caacd27808
Testing again. Closes : #35
2002-05-03 03:28:21 +00:00
5a1a2287f6
Doesn't do anything more, just looks a little prettier. Closes : #35
2002-05-03 03:13:12 +00:00
54fb180fad
expr.h:
...
__attribute__((const)) has rather nasty results when it's not true
expr.c:
fix up some mis-timed ex_error checks
2002-05-02 05:03:57 +00:00
05788e55e5
don't generate useless expression warnings when that expression was caused
...
by an error
2002-05-01 22:08:59 +00:00
a9f3814c86
forgot to remove scope.h
2002-05-01 21:48:23 +00:00
067359b39d
d'oh, missed a ;
2002-05-01 21:42:29 +00:00
962dc8e46e
rewrite the type and def parsing to allow more flexible types
2002-05-01 21:35:39 +00:00
Bill Currie
Jeff Teunissen
Ragnvald Maartmann-Moe IV
Chris Ison