Commit 2a52475f authored by Markus Koschany's avatar Markus Koschany

Imported Upstream version 0.11a+20060608

parent 620e3138
<project name="emugen" default ="dist" basedir=".">
<property name="etc" location="etc" />
<property name="bin" location="bin" />
<property name="lib" location="lib" />
<property name="src" location="src" />
<property name="java" location="java" />
<property name="classes" location="classes" />
<property name="dist" location="dist" />
<!--property name="test" location="test" /-->
<property name="flex" location="flex" />
<property name="cup" location="cup" />
<!-- initialize the workspace -->
<target name="init">
<tstamp />
<mkdir dir="${src}" />
<mkdir dir="${java}" />
<mkdir dir="${classes}" />
<mkdir dir="${dist}" />
<property environment="env" />
<path id="libraries">
<pathelement location="${src}" />
<fileset dir="${lib}">
<include name="**/*.jar" />
<path id="binaries">
<fileset dir="${bin}">
<include name="**/*.jar" />
<target name="clean">
<delete dir="${java}" />
<delete dir="${classes}" />
<delete dir="${dist}" />
<taskdef name="cup" classname="java_cup.anttask.CUPTask" classpath="${bin}/java-cup-11.jar" />
<taskdef name="jflex" classname="JFlex.anttask.JFlexTask" classpath="${bin}/JFlex.jar" />
<target name="cup" depends="init">
<cup srcfile="${cup}/parser.cup" interface="on" destdir="${java}" parser="parser" symbols="sym" quiet="false" nonterms="true"/>
<target name="jflex" depends="cup">
<jflex file="${flex}/Lexer.jflex" destdir="${java}" />
<target name="compile" depends="jflex">
<copy todir="${java}"><fileset dir="${src}"></fileset></copy>
<javac srcdir="${java}" destdir="${classes}" verbose="off" listfiles="off" debug="on" source="1.2" target="1.2">
<classpath refid="libraries"/>
<target name="dist" depends="compile">
<jar jarfile="${dist}/java-cup-11a.jar" basedir="${classes}">
<attribute name="Main-Class" value="java_cup/Main" />
<attribute name="Class-Path" value="java-cup-11a-runtime.jar" />
<jar jarfile="${dist}/java-cup-11a-runtime.jar" basedir="${classes}" includes="java_cup/runtime/*">
<target name="test" depends="dist">
<java jar="${dist}/java-cup-11a.jar" fork="true">
<arg value="-interface" />
<arg value="${cup}/parser.cup" />
CUP version 0.11a beta 20060608 is a bugfix release.
Embedded actions in CUP didn't really relay their intermediate results to the
main action part. now, embedded actions have the following (new) properties:
- the LHS has the type of the "parent" lhs
- the RESULT variable of following embedded actions have their RESULT
variables initialized with the RESULT of the previous embedded action
M. Petter, A. Flexeder
Technische Universität München
CUP version 0.11a beta 200603230 is a bugfix release.
corrected new issue with SymbolFactory. Forgot to offer one of the non-
propagating factory methods for Symbol generation. (thanks to )
M. Petter
Technische Universität München
CUP version 0.11a beta 20060328 is a feature release.
Introduced the concept of the java_cup.runtime.SymbolFactory, which serves
multiple purposes; now You have the chance to manage extended information
relating to the sourcecode file in Your symbols, by using own child classes
of java_cup.runtime.Symbol.
In Addition to that You can implement Your own child class of SymbolFactory
to have a callback function whenever a new Symbol is created. This is
especially handy when equipping Your syntax tree with location information
from the source code file. For exactly this purpose the new Factories
java_cup.runtime.DefaultSymbolFactory and
are introduced.
Experiments with the new runtime have revealed a few little flaws in the
build file, resulting in classpath confusion: In fact, JFlex itself depends
on the CUP runtime, leading to a mixture of runtimes, that could spoil Your
build process. I have corrected the errors in the CUP buildfile.
M. Petter
Technische Universität München
CUP version 0.11a beta 20060102 is a bugfix release.
Corrected two minor issues: a build.xml bug resulting in a slightly smaller
runtime JAR (thanks to Florian ) and an
incorrect initialized parameter (thanks to Andreas
M. Petter
Technische Universität München
CUP version 0.11a beta 20051104 is a bugfix release.
the buildfile now creates Java 1.2 compliant code as well as it uses an actual
JDK 1.2 compliant CUP version for bootstrapping. has
contributed to bugfixes, concerning an ant parameter as well as a more
informative CODE_STRING Token.
M. Petter
Technische Universität München
CUP version 0.11a beta 20050921 is a combined bugfix release.
added calls to clear the content of static fields in CUP, to be able to
call the main() method several times instead of only one time without
strange errors.
M. Petter
Technische Universität München
CUP version 0.11a beta 20050920 is a combined bugfix/feature release.
Made use of .peek() function for Stacks in generated parsers.
-destdir parameter added for generation in Makefiles or with ant.
Completely rewrote the CUP-anttask to properly call ant even, if You use
paths including whitespaces.
M. Petter
Technische Universität München
CUP version 0.11a beta 20050628 is a combined bugfix/feature release.
Henning Niss ( hniss at itu dot dk ) sent me a patch to improve the
generics handling in CUP. It also introduces a new parameter
"-typeargs" to cup, whith which one can parametrize the generated parser.
M. Petter
Technische Universität München
CUP version 0.11a beta 20050516 is a management release.
To indicate, that the CUP project switches from the Princeton team to the
technical university of munich, we switch to version 11 since this moment.
Nothing else has changed since the last bugfix release, as indicated in
the version date.
M. Petter
Technische Universität München
CUP version 0.10k TUM Edition 20050516 is a bugfix release.
We forgot to implement a simple line in the wildcard production integration,
leading to wildcards like ArrayList<? extends MyClass> being
destroyed. Meanwhile, everything should work as it is supposed to.
M. Petter
Technische Universität München
CUP version 0.10k TUM Edition 20050514 is a bugfix/enhancement release.
Along with the redesigned Lexer, CUP lost a lot of error tracking and
displaying capabilities; now we have redesigned the Errormanager to display
even better error informations like column/line and the token in plain text,
CUP is processing, when the error occurs.
M. Petter
Technische Universität München
CUP version 0.10k TUM Edition 20050510 is a feature release.
CUP now supports generic parametrisation of datatypes for CUP terminals
and non terminals, as provided by Java 1.5. We do hope, it works correctly
all flavours of Java generics, as for example wildcards.
! Be carefull ! : there are the new keywords "super" and "extends", which
had to be introduced to support generic types. Watch out for identifiers in
Your CUP files, that have these names.
There is now an ANT Task for CUP, namely java_cup.anttask.CUPTask. It will
soon be added to the documentation - for the moment, You can look into the
sources to figure out, how to use it.
The CUP frontend, which parses .cup-files has changed to a JFlex-generated
scanner, which allows an easier maintainance.
M. Petter
Technische Universität München
CUP version 0.10k is a maintenance release.
CUP will now accept a filename on the command-line if it is the last
argument and does not start with "-". This allows better GUI
integration. Some unix-isms in end-of-line handling have been fixed,
too; thanks to Jean Vaucher <> for the tip.
The java_cup.runtime.Scanner interface has been refined to allow
the scanner to return null to signal EOF. JLex and JFlex users will
like this, as it means they can use the default scanner EOF behavior.
Bruce Hutton <>, Zerksis Umrigar <>,
and Vladimir Antonevich <> all sent bug
reports touching on erroneous error recovery in the parser runtime.
Dr. Hutton provided the fixes that I've adopted; Zerksis sent a very
helpful CUP-vs-bison test case. If you're in a position to notice
correct/incorrect error recovery and this release works better for you
than previous ones, thank them --- and send me email so I know whether
we've quashed this bug for good.
Klaus Georg Barthelmann <barthel@Informatik.Uni-Mainz.DE> caught an
oversight in the constructors for java_cup.runtime.Symbol. I've also
taken an obsolete constructor allowing specification of a start state
for some symbol to package-scope; if this causes anyone backwards
compatibility problems, email me and I will consider changing it back.
C. Scott Ananian
Laboratory for Computer Science
Massachusetts Institute of Technology
Jul-24-1999 [CSA]
CUP version 0.10j adds new features.
A "-version" command-line option is now accepted, which prints out the
working version of CUP and halts. This allows automatic version-checking,
for those applications which require it.
Broadened the CUP input grammar to allow CUP reserved words in package and
import statements, and in (non)terminal labels. In addition, semicolons
after 'action code', 'parser code', 'init code', and 'scan with' sections
have been made optional (if language noise annoys you). Also, these four
sections may now appear in any order, instead of the strict ordering
previously required. Finally, you can now spell 'non-terminal' as either
"non terminal" (old way) *or* "nonterminal" without upsetting CUP.
[Flexibility requested by Stefan Kahrs <>]
[Package and import reserved word issues noted by Frank Rehberger,
Brandon Schendel, and Bernie Honeisen, among others.]
Clarified the parse table dumps generated by the -dump* options.
I have added code to lr_parser to detect illegal Symbol recycling by the
scanner and to throw an Error in this case. The scanner must return
a fresh Symbol object on each invocation, because these objects are
tagged with parse state and added to the parse stack. Object sharing
does evil things to the parser; don't do it (you won't get away with it).
[Symbol recycling problems reported by Ken Arnold <Ken.Arnold@Sun.COM>]
Improved scanner interface, designed by David MacMahon <>.
The new java_cup.runtime.Scanner interface is used by the default
implementation of lr_parser.scan(). See the manual for more details.
Old parsers will work with the new runtime, but parsers generated with
0.10j will not work with the runtime from earlier versions unless you
specify the (new) "-noscanner" option.
C. Scott Ananian
Laboratory for Computer Science
Massachusetts Institute of Technology
Jul-24-1999 [CSA]
CUP version 0.10i is a maintenance release.
A one-off bug in the parser error-recovery code has been caught and corrected
by Chris Harris <>.
The fields in the emitted symbol class have been made public, rather than
package scope, since the class already was public.
The issues formerly addressed in Appendix D (accessing parser methods/fields
from the action class) have been partially addressed by adding a new
private final field named 'parser' to the action object that points to
previously defined a field named 'parser' in the 'action code {: ... :}'
portion of your grammar. The solution is to rename your field.
Finally, incorporated Jako Andras' suggestions to make CUP more friendly
to makefiles.
A reminder: please submit bug-fixes or feature-additions as *patches*, not
complete archives. Your patch will have a greater chance of integration
into the distribution if you package each feature or fix as a separate patch,
instead of lumping everything together and leaving it to me to figure out
what you've changed and why.
C. Scott Ananian
Laboratory for Computer Science
Massachusetts Institute of Technology
Feb-18-1999 [CSA]
CUP version 0.10h is a maintenance release.
Starting with this version, CUP encodes the various parser tables as strings
to get around java's 64k method-size limitation. This allows larger
parse tables and thus more complicated grammars.
Furthermore, a long-standing buglet that would cause CUP to occasionally
generate "Attempt to construct a duplicate state" internal errors has been
Another contributed Microsoft-compatible makefile has also been added
to the distribution.
C. Scott Ananian
Laboratory for Computer Science
Massachusetts Institute of Technology
Feb-10-1999 [CSA]
CUP version 0.10g contains bug fixes, added functionality, and
performance improvements. Thanks to Matthias Zenger, Peter Selinger,
Jaroslaw Kachinarz, Ian Davis and others for contributions.
- New command line option '-interface' added. This causes JavaCUP to
emit an *interface* with the symbol constants, instead of a
*class*. Without the command-line flag, behavior is identical to
v0.10f and before: the symbols are emitted as a class.
- (minor) Added toString() method to java_cup.runtime.Symbol and
modified the debugging parser to use it. This allows you to
override toString() to allow a more intelligible debugging parse.
- The CUP grammar has been extended to allow one to declare array types
for javaCUP terminals and non-terminals. Matthias Zenger first
suggested this feature; Peter Selinger was the first to show the
right way to do it.
- The symbols prefixed with CUP$ now have the parser class file name
added to the prefix as well, to allow more than one parser object
per package. Thanks to Jaroslaw Kachniarz for pointing out this
- Fixed bug that prevented one from invoking the parser multiple times.
To quote Ian Davis, who found and diagnosed the bug:
Repeat invocations of the same instantiation of to parse
distinct input statements fail for the simple reason that the stack is
not emptied at start of parsing, but the stack offset is reset to 0.
This has been fixed.
- Fixed bug with implicit start productions not receiving a RESULT.
- Fixed bug with RESULT assignments that are not right-most in the
- Updated documentation.
Known issues:
- All known bugs have been fixed.
- The java_cup.runtime.SymbolStack / java_cup.runtime.intStack
performance hack originally suggested by Matthias Zenger has been
postponed to the next release. By eliminating typecasts and
synchronized methods, a substantial performance improvement can be
obtained. Backwards-compatibility issues have forced the postponement
of the code merge.
C. Scott Ananian
Laboratory for Computer Science
Massachusetts Institute of Technology
3/24/98 [CSA]
CUP version 0.10f is a maintenance release. The code has been cleaned up
for JDK 1.1 functionality. No major functionality has been added; any bugs
in 0.10e are still in 0.10f.
- Removed trailing semicolons from class definitions which upset strict
compilers (not Sun's javac, for some reason).
- Changed 'PrintStream's to 'PrintWriter's to eliminate deprecation
As of this release, the javaCUP code is being maintained by
C. Scott Ananian. Suggestions and bug-fixes should be sent to
Known issues:
- Precedence bug: rules unmarked by precedence information are treated
as if they had existing, but very low, precedence. This can mask
parser conflicts.
- Efficiency hack: java.util.Stack will be replaced in the next
release with a special-purpose stack to eliminate
performance-robbing type-casts.
- It has been suggested that the symbol *class* should be an
*interface* instead. This will be a command-line option in the next
C. Scott Ananian
Laboratory for Computer Science
Massachusetts Institute of Technology
12/21/97 [CSA]
CUP version 0.10e contains a few bug fixes from 0.10a
- %prec directive now works correctly
fixed by <C. Scott Ananian>
- Shift reduce conflicts are now correctly reported
fixed by <Daniel . Wang>
- Error with reporting the positon of the error token also fixed
fixed by <C. Scott Ananian>
- INSTALL script now has a slightly more complex test.
- included for changes from previous release
- Fixed more bugs with reporting of shift reduce conflicts.
fixed by <Daniel . Wang>
- Fixed bug introduced by previous fix patches from <>
Added '\r' as a whitespace character for the lexer suggested by
- Fixed botched relase
Daniel Wang
Department of Computer Science
Princeton University
Last updated: 9/12/97 [DW]
Changes and Additions to CUP v0.9e
CUP version 0.10a is a major overhaul of CUP. The changes are severe,
meaning no backwards compatibility to older versions.
Here are the changes:
1. CUP now interfaces with the lexer in a completely different
manner. In the previous releases, a new class was used for every
distinct type of terminal. This release, however, uses only one class:
The Symbol class. The Symbol class has three instance variables which
are significant to the parser when passing information from the lexer.
The first is the value instance variable. This variable contains the
value of that terminal. It is of the type declared as the terminal type
in the parser specification file. The second two are the instance
variables left and right. They should be filled with the int value of
where in the input file, character-wise, that terminal was found.
2. Terminal and non-nonterminal declarations now can be declared in two
different ways to indicate the values of the terminals or non-terminals.
The previous declarations of the form
terminal {classname} {terminal} [, terminal ...];
still works. The classname, however indicates the type of the value of
the terminal or non-terminal, and does not indicate the type of object
placed on the parse stack.
A declaration, such as:
terminal {terminal} [, terminal ...];
indicates the terminals in the list hold no value.
3. CUP doesn't use the Symbol class for just terminals, but for all
non-terminals as well. When a production reduces to a non-terminal, a
new Symbol is created, and the value field is filled with the value of
that non-terminal. The user must know that the terminal and non terminal
declarations specify a type corresponding to the type of the value field
for the symbol representing that terminal or non-terminal.
4. Label references do not refer to the object on the parse stack, as in
the old CUP, but rather to the value of the value instance variable of
the Symbol that represents that terminal or non-terminal. Hence,
references to terminal and non-terminal values is direct, as opposed to
the old CUP, where the labels referred to objects containing the value
of the terminal or non-terminal.
5. The RESULT variable refers directly to the value of the non-terminal
to which a rule reduces, rather than to the object on the parse stack.
Hence, RESULT is of the same type the non-terminal to which it reduces,
as declared in the non terminal declaration. Again, the reference is
direct, rather than to something that will contain the data.
6. For every label, two more variables are declared, which are the label
plus left or the label plus right. These correspond to the left and
right locations in the input stream to which that terminal or
non-terminal came from. These values are propagated from the input
terminals, so that the starting non-terminal should have a left value of
0 and a right value of the location of the last character read.
7. A call to parse() or debug_parse() return a Symbol. This Symbol is
of the start non-terminal, so the value field contains the final RESULT
8. CUP now has precedenced terminals. a new declaration section,
occurring between the terminal and non-terminal declarations and the
grammar specifies the precedence and associativity of rules. The
declarations are of the form:
precedence {left| right | nonassoc} terminal[, terminal ...];
The terminals are assigned a precedence, where terminals on the same
line have equal precedences, and the precedence declarations farther
down the list of precedence declarations have higher precedence. left,
right and nonassoc specify the associativity of these terminals. left
associativity corresponds to a reduce on conflict, right to a shift on
conflict, and nonassoc to an error on conflict. Hence, ambiguous
grammars may now be used. For a better explanation, see the manual.
9. Finally the new CUP adds contextual precedence. A production may be
declare as followed:
lhs ::= {right hand side list of terminals, non-terminals and actions}
%prec {terminal};
this production would then have a precedence equal to the terminal
specified after the "%prec". Hence, shift/reduce conflicts can be
contextually resolved. Note that the "%prec terminal" part comes after
all actions strings. It does not come before the last action string.
For more information read the manual, found in manual.html
Frank Flannery
Department of Computer Science
Princeton University
Last updated: 7/3/96 [FF]
JavaCup Specification for the JavaCup Specification Language
by Scott Hudson, GVU Center, Georgia Tech, August 1995
and Frank Flannery, Department of Computer Science, Princeton Univ,
July 1996
Bug Fixes: C. Scott Ananian, Dept of Electrical Engineering, Princeton
University, October 1996. [later Massachusetts Institute of Technology]
This JavaCup specification is used to implement JavaCup itself.
It specifies the parser for the JavaCup specification language.
(It also serves as a reasonable example of what a typical JavaCup
spec looks like).
The specification has the following parts:
Package and import declarations
These serve the same purpose as in a normal Java source file
(and will appear in the generated code for the parser). In this
case we are part of the java_cup package and we import both the
java_cup runtime system and Hashtable from the standard Java
utilities package.
Action code
This section provides code that is included with the class encapsulating
the various pieces of user code embedded in the grammar (i.e., the
semantic actions). This provides a series of helper routines and
data structures that the semantic actions use.
Parser code
This section provides code included in the parser class itself. In
this case we override the default error reporting routines.
Init with and scan with
These sections provide small bits of code that initialize, then
indicate how to invoke the scanner.
Symbols and grammar
These sections declare all the terminal and non terminal symbols
and the types of objects that they will be represented by at runtime,
then indicate the start symbol of the grammar (), and finally provide
the grammar itself (with embedded actions).
Operation of the parser
The parser acts primarily by accumulating data structures representing
various parts of the specification. Various small parts (e.g., single
code strings) are stored as static variables of the emit class and
in a few cases as variables declared in the action code section.
Terminals, non terminals, and productions, are maintained as collection
accessible via static methods of those classes. In addition, two
symbol tables are kept:
symbols maintains the name to object mapping for all symbols
non_terms maintains a separate mapping containing only the non terms
Several intermediate working structures are also declared in the action
code section. These include: rhs_parts, rhs_pos, and lhs_nt which
build up parts of the current production while it is being parsed.
Scott Hudson, GVU Center, Georgia Tech.
Frank Flannery, Department of Computer Science, Princeton Univ.
C. Scott Ananian, Department of Electrical Engineering, Princeton Univ.
v0.9a First released version [SEH] 8/29/95
v0.9b Updated for beta language (throws clauses) [SEH] 11/25/95
v0.10a Made many improvements/changes. now offers:
return value
left/right positions and propagations
cleaner label references
precedence and associativity for terminals
contextual precedence for productions
[FF] 7/3/96
v0.10b Fixed %prec directive so it works like it's supposed to.
[CSA] 10/10/96
v0.10g Added support for array types on symbols.
[CSA] 03/23/98
v0.10i Broaden set of IDs allowed in multipart_id and label_id so
that only java reserved words (and not CUP reserved words like
'parser' and 'start') are prohibited. Allow reordering of
action code, parser code, init code, and scan with sections,
and made closing semicolon optional for these sections.
Added 'nonterminal' as a terminal symbol, finally fixing a
spelling mistake that's been around since the beginning.
For backwards compatibility, you can still misspell the
word if you like.
package java_cup;
import java_cup.runtime.*;
import java.util.Hashtable;
import java.util.Stack;
action code {:
/** helper routine to clone a new production part adding a given label */
protected production_part add_lab(production_part part, String lab)
throws internal_error
/* if there is no label, or this is an action, just return the original */
if (lab == null || part.is_action()) return part;
/* otherwise build a new one with the given label attached */
return new symbol_part(((symbol_part)part).the_symbol(),lab);
/** max size of right hand side we will support */
protected final int MAX_RHS = 200;
/** array for accumulating right hand side parts */
protected production_part[] rhs_parts = new production_part[MAX_RHS];
/** where we are currently in building a right hand side */
protected int rhs_pos = 0;
/** start a new right hand side */
protected void new_rhs() {rhs_pos = 0; }
/** add a new right hand side part */
protected void add_rhs_part(production_part part) throws java.lang.Exception
if (rhs_pos >= MAX_RHS)
throw new Exception("Internal Error: Productions limited to " +
MAX_RHS + " symbols and actions");
rhs_parts[rhs_pos] = part;
/** string to build up multiple part names */
protected String multipart_name = new String();
protected Stack multipart_names = new Stack();
/** append a new name segment to the accumulated multipart name */
// protected void append_multipart(String name)
// {
// String dot = "";
// /* if we aren't just starting out, put on a dot */
// if (multipart_name.length() != 0) dot = ".";
// multipart_name = multipart_name.concat(dot + name);
// }
/** table of declared symbols -- contains production parts indexed by name */
protected Hashtable symbols = new Hashtable();
/** table of just non terminals -- contains non_terminals indexed by name */
protected Hashtable non_terms = new Hashtable();
/** declared start non_terminal */
protected non_terminal start_nt = null;
/** left hand side non terminal of the current production */
protected non_terminal lhs_nt;
/** Current precedence number */
int _cur_prec = 0;
/** Current precedence side */
int _cur_side = assoc.no_prec;
/** update the precedences we are declaring */
protected void update_precedence(int p) {
_cur_side = p;
/** add relevant data to terminals */
protected void add_precedence(String term) {
if (term == null) {
System.err.println("Unable to add precedence to nonexistent terminal");
} else {
symbol_part sp = (symbol_part)symbols.get(term);
if (sp == null) {
System.err.println("Could find terminal " + term + " while declaring precedence");
} else {
java_cup.symbol sym = sp.the_symbol();
if (sym instanceof terminal)
((terminal)sym).set_precedence(_cur_side, _cur_prec);
else System.err.println("Precedence declaration: Can't find terminal " + term);
/*. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . */
parser code {:
/* override error routines */
protected Lexer lexer;
public void report_fatal_error(
String message,
Object info)
if (info instanceof Symbol) ErrorManager.getManager().emit_fatal(message+ "\nCan't recover from previous error(s), giving up.",(Symbol)info);
else ErrorManager.getManager().emit_fatal(message + "\nCan't recover from previous error(s), giving up.",cur_token);
public void report_error(String message, Object info)
if (info instanceof Symbol)
/*---------------------------------------------------------------- */