sanchayanmaity/gem5
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Update to ply 2.3

Browse source 
ext/ply/ply/lex.py:
ext/ply/ply/yacc.py:
ext/ply/CHANGES:
ext/ply/README:
ext/ply/TODO:
ext/ply/doc/ply.html:
ext/ply/example/ansic/clex.py:
ext/ply/example/ansic/cparse.py:
ext/ply/example/calc/calc.py:
ext/ply/example/hedit/hedit.py:
ext/ply/example/optcalc/calc.py:
ext/ply/test/README:
ext/ply/test/calclex.py:
ext/ply/test/lex_doc1.exp:
ext/ply/test/lex_doc1.py:
ext/ply/test/lex_dup1.exp:
ext/ply/test/lex_dup1.py:
ext/ply/test/lex_dup2.exp:
ext/ply/test/lex_dup2.py:
ext/ply/test/lex_dup3.exp:
ext/ply/test/lex_dup3.py:
ext/ply/test/lex_empty.py:
ext/ply/test/lex_error1.py:
ext/ply/test/lex_error2.py:
ext/ply/test/lex_error3.exp:
ext/ply/test/lex_error3.py:
ext/ply/test/lex_error4.exp:
ext/ply/test/lex_error4.py:
ext/ply/test/lex_hedit.exp:
ext/ply/test/lex_hedit.py:
ext/ply/test/lex_ignore.exp:
ext/ply/test/lex_ignore.py:
ext/ply/test/lex_re1.exp:
ext/ply/test/lex_re1.py:
ext/ply/test/lex_rule1.py:
ext/ply/test/lex_token1.py:
ext/ply/test/lex_token2.py:
ext/ply/test/lex_token3.py:
ext/ply/test/lex_token4.py:
ext/ply/test/lex_token5.exp:
ext/ply/test/lex_token5.py:
ext/ply/test/yacc_badargs.exp:
ext/ply/test/yacc_badargs.py:
ext/ply/test/yacc_badprec.exp:
ext/ply/test/yacc_badprec.py:
ext/ply/test/yacc_badprec2.exp:
ext/ply/test/yacc_badprec2.py:
ext/ply/test/yacc_badrule.exp:
ext/ply/test/yacc_badrule.py:
ext/ply/test/yacc_badtok.exp:
ext/ply/test/yacc_badtok.py:
ext/ply/test/yacc_dup.exp:
ext/ply/test/yacc_dup.py:
ext/ply/test/yacc_error1.exp:
ext/ply/test/yacc_error1.py:
ext/ply/test/yacc_error2.exp:
ext/ply/test/yacc_error2.py:
ext/ply/test/yacc_error3.exp:
ext/ply/test/yacc_error3.py:
ext/ply/test/yacc_inf.exp:
ext/ply/test/yacc_inf.py:
ext/ply/test/yacc_missing1.exp:
ext/ply/test/yacc_missing1.py:
ext/ply/test/yacc_nodoc.exp:
ext/ply/test/yacc_nodoc.py:
ext/ply/test/yacc_noerror.exp:
ext/ply/test/yacc_noerror.py:
ext/ply/test/yacc_nop.exp:
ext/ply/test/yacc_nop.py:
ext/ply/test/yacc_notfunc.exp:
ext/ply/test/yacc_notfunc.py:
ext/ply/test/yacc_notok.exp:
ext/ply/test/yacc_notok.py:
ext/ply/test/yacc_rr.exp:
ext/ply/test/yacc_rr.py:
ext/ply/test/yacc_simple.exp:
ext/ply/test/yacc_simple.py:
ext/ply/test/yacc_sr.exp:
ext/ply/test/yacc_sr.py:
ext/ply/test/yacc_term1.exp:
ext/ply/test/yacc_term1.py:
ext/ply/test/yacc_unused.exp:
ext/ply/test/yacc_unused.py:
ext/ply/test/yacc_uprec.exp:
ext/ply/test/yacc_uprec.py:
    Import patch ply.diff
src/arch/isa_parser.py:
    everything is now within the ply package

--HG--
rename : ext/ply/lex.py => ext/ply/ply/lex.py
rename : ext/ply/yacc.py => ext/ply/ply/yacc.py
extra : convert_revision : fca8deabd5c095bdeabd52a1f236ae1404ef106e
This commit is contained in:
Nathan Binkert 2007-05-24 21:54:51 -07:00
parent 9f1c104ccd
commit 44ebb8d3e2
145 changed files with 7739 additions and 1534 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
ext/ply/ANNOUNCE Normal file
View file

@ -0,0 +1,48 @@
February 19, 2007
Announcing : PLY-2.3 (Python Lex-Yacc)
http://www.dabeaz.com/ply
I'm pleased to announce a significant new update to PLY---a 100% Python
implementation of the common parsing tools lex and yacc. PLY-2.3 is
a minor bug fix release, but also features improved performance.
If you are new to PLY, here are a few highlights:
- PLY is closely modeled after traditional lex/yacc. If you know how
to use these or similar tools in other languages, you will find
PLY to be comparable.
- PLY provides very extensive error reporting and diagnostic
information to assist in parser construction. The original
implementation was developed for instructional purposes. As
a result, the system tries to identify the most common types
of errors made by novice users.
- PLY provides full support for empty productions, error recovery,
precedence rules, and ambiguous grammars.
- Parsing is based on LR-parsing which is fast, memory efficient,
better suited to large grammars, and which has a number of nice
properties when dealing with syntax errors and other parsing
problems. Currently, PLY can build its parsing tables using
either SLR or LALR(1) algorithms.
- PLY can be used to build parsers for large programming languages.
Although it is not ultra-fast due to its Python implementation,
PLY can be used to parse grammars consisting of several hundred
rules (as might be found for a language like C). The lexer and LR
parser are also reasonably efficient when parsing normal
sized programs.
More information about PLY can be obtained on the PLY webpage at:
http://www.dabeaz.com/ply
PLY is freely available and is licensed under the terms of the Lesser
GNU Public License (LGPL).
Cheers,
David Beazley (http://www.dabeaz.com)

579
ext/ply/CHANGES
View file

@ -1,3 +1,582 @@
Version 2.3
-----------------------------
02/20/07: beazley
Fixed a bug with character literals if the literal '.' appeared as the
last symbol of a grammar rule. Reported by Ales Smrcka.
02/19/07: beazley
Warning messages are now redirected to stderr instead of being printed
to standard output.
02/19/07: beazley
Added a warning message to lex.py if it detects a literal backslash
character inside the t_ignore declaration. This is to help
problems that might occur if someone accidentally defines t_ignore
as a Python raw string. For example:
t_ignore = r' \t'
The idea for this is from an email I received from David Cimimi who
reported bizarre behavior in lexing as a result of defining t_ignore
as a raw string by accident.
02/18/07: beazley
Performance improvements. Made some changes to the internal
table organization and LR parser to improve parsing performance.
02/18/07: beazley
Automatic tracking of line number and position information must now be
enabled by a special flag to parse(). For example:
yacc.parse(data,tracking=True)
In many applications, it's just not that important to have the
parser automatically track all line numbers. By making this an
optional feature, it allows the parser to run significantly faster
(more than a 20% speed increase in many cases). Note: positional
information is always available for raw tokens---this change only
applies to positional information associated with nonterminal
grammar symbols.
*** POTENTIAL INCOMPATIBILITY ***
02/18/07: beazley
Yacc no longer supports extended slices of grammar productions.
However, it does support regular slices. For example:
def p_foo(p):
'''foo: a b c d e'''
p[0] = p[1:3]
This change is a performance improvement to the parser--it streamlines
normal access to the grammar values since slices are now handled in
a __getslice__() method as opposed to __getitem__().
02/12/07: beazley
Fixed a bug in the handling of token names when combined with
start conditions. Bug reported by Todd O'Bryan.
Version 2.2
------------------------------
11/01/06: beazley
Added lexpos() and lexspan() methods to grammar symbols. These
mirror the same functionality of lineno() and linespan(). For
example:
def p_expr(p):
'expr : expr PLUS expr'
p.lexpos(1) # Lexing position of left-hand-expression
p.lexpos(1) # Lexing position of PLUS
start,end = p.lexspan(3) # Lexing range of right hand expression
11/01/06: beazley
Minor change to error handling. The recommended way to skip characters
in the input is to use t.lexer.skip() as shown here:
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.lexer.skip(1)
The old approach of just using t.skip(1) will still work, but won't
be documented.
10/31/06: beazley
Discarded tokens can now be specified as simple strings instead of
functions. To do this, simply include the text "ignore_" in the
token declaration. For example:
t_ignore_cppcomment = r'//.*'
Previously, this had to be done with a function. For example:
def t_ignore_cppcomment(t):
r'//.*'
pass
If start conditions/states are being used, state names should appear
before the "ignore_" text.
10/19/06: beazley
The Lex module now provides support for flex-style start conditions
as described at http://www.gnu.org/software/flex/manual/html_chapter/flex_11.html.
Please refer to this document to understand this change note. Refer to
the PLY documentation for PLY-specific explanation of how this works.
To use start conditions, you first need to declare a set of states in
your lexer file:
states = (
('foo','exclusive'),
('bar','inclusive')
)
This serves the same role as the %s and %x specifiers in flex.
One a state has been declared, tokens for that state can be
declared by defining rules of the form t_state_TOK. For example:
t_PLUS = '\+' # Rule defined in INITIAL state
t_foo_NUM = '\d+' # Rule defined in foo state
t_bar_NUM = '\d+' # Rule defined in bar state
t_foo_bar_NUM = '\d+' # Rule defined in both foo and bar
t_ANY_NUM = '\d+' # Rule defined in all states
In addition to defining tokens for each state, the t_ignore and t_error
specifications can be customized for specific states. For example:
t_foo_ignore = " " # Ignored characters for foo state
def t_bar_error(t):
# Handle errors in bar state
With token rules, the following methods can be used to change states
def t_TOKNAME(t):
t.lexer.begin('foo') # Begin state 'foo'
t.lexer.push_state('foo') # Begin state 'foo', push old state
# onto a stack
t.lexer.pop_state() # Restore previous state
t.lexer.current_state() # Returns name of current state
These methods mirror the BEGIN(), yy_push_state(), yy_pop_state(), and
yy_top_state() functions in flex.
The use of start states can be used as one way to write sub-lexers.
For example, the lexer or parser might instruct the lexer to start
generating a different set of tokens depending on the context.
example/yply/ylex.py shows the use of start states to grab C/C++
code fragments out of traditional yacc specification files.
*** NEW FEATURE *** Suggested by Daniel Larraz with whom I also
discussed various aspects of the design.
10/19/06: beazley
Minor change to the way in which yacc.py was reporting shift/reduce
conflicts. Although the underlying LALR(1) algorithm was correct,
PLY was under-reporting the number of conflicts compared to yacc/bison
when precedence rules were in effect. This change should make PLY
report the same number of conflicts as yacc.
10/19/06: beazley
Modified yacc so that grammar rules could also include the '-'
character. For example:
def p_expr_list(p):
'expression-list : expression-list expression'
Suggested by Oldrich Jedlicka.
10/18/06: beazley
Attribute lexer.lexmatch added so that token rules can access the re
match object that was generated. For example:
def t_FOO(t):
r'some regex'
m = t.lexer.lexmatch
# Do something with m
This may be useful if you want to access named groups specified within
the regex for a specific token. Suggested by Oldrich Jedlicka.
10/16/06: beazley
Changed the error message that results if an illegal character
is encountered and no default error function is defined in lex.
The exception is now more informative about the actual cause of
the error.
Version 2.1
------------------------------
10/02/06: beazley
The last Lexer object built by lex() can be found in lex.lexer.
The last Parser object built by yacc() can be found in yacc.parser.
10/02/06: beazley
New example added: examples/yply
This example uses PLY to convert Unix-yacc specification files to
PLY programs with the same grammar. This may be useful if you
want to convert a grammar from bison/yacc to use with PLY.
10/02/06: beazley
Added support for a start symbol to be specified in the yacc
input file itself. Just do this:
start = 'name'
where 'name' matches some grammar rule. For example:
def p_name(p):
'name : A B C'
...
This mirrors the functionality of the yacc %start specifier.
09/30/06: beazley
Some new examples added.:
examples/GardenSnake : A simple indentation based language similar
to Python. Shows how you might handle
whitespace. Contributed by Andrew Dalke.
examples/BASIC : An implementation of 1964 Dartmouth BASIC.
Contributed by Dave against his better
judgement.
09/28/06: beazley
Minor patch to allow named groups to be used in lex regular
expression rules. For example:
t_QSTRING = r'''(?P<quote>['"]).*?(?P=quote)'''
Patch submitted by Adam Ring.
09/28/06: beazley
LALR(1) is now the default parsing method. To use SLR, use
yacc.yacc(method="SLR"). Note: there is no performance impact
on parsing when using LALR(1) instead of SLR. However, constructing
the parsing tables will take a little longer.
09/26/06: beazley
Change to line number tracking. To modify line numbers, modify
the line number of the lexer itself. For example:
def t_NEWLINE(t):
r'\n'
t.lexer.lineno += 1
This modification is both cleanup and a performance optimization.
In past versions, lex was monitoring every token for changes in
the line number. This extra processing is unnecessary for a vast
majority of tokens. Thus, this new approach cleans it up a bit.
*** POTENTIAL INCOMPATIBILITY ***
You will need to change code in your lexer that updates the line
number. For example, "t.lineno += 1" becomes "t.lexer.lineno += 1"
09/26/06: beazley
Added the lexing position to tokens as an attribute lexpos. This
is the raw index into the input text at which a token appears.
This information can be used to compute column numbers and other
details (e.g., scan backwards from lexpos to the first newline
to get a column position).
09/25/06: beazley
Changed the name of the __copy__() method on the Lexer class
to clone(). This is used to clone a Lexer object (e.g., if
you're running different lexers at the same time).
09/21/06: beazley
Limitations related to the use of the re module have been eliminated.
Several users reported problems with regular expressions exceeding
more than 100 named groups. To solve this, lex.py is now capable
of automatically splitting its master regular regular expression into
smaller expressions as needed. This should, in theory, make it
possible to specify an arbitrarily large number of tokens.
09/21/06: beazley
Improved error checking in lex.py. Rules that match the empty string
are now rejected (otherwise they cause the lexer to enter an infinite
loop). An extra check for rules containing '#' has also been added.
Since lex compiles regular expressions in verbose mode, '#' is interpreted
as a regex comment, it is critical to use '\#' instead.
09/18/06: beazley
Added a @TOKEN decorator function to lex.py that can be used to
define token rules where the documentation string might be computed
in some way.
digit = r'([0-9])'
nondigit = r'([_A-Za-z])'
identifier = r'(' + nondigit + r'(' + digit + r'|' + nondigit + r')*)'
from ply.lex import TOKEN
@TOKEN(identifier)
def t_ID(t):
# Do whatever
The @TOKEN decorator merely sets the documentation string of the
associated token function as needed for lex to work.
Note: An alternative solution is the following:
def t_ID(t):
# Do whatever
t_ID.__doc__ = identifier
Note: Decorators require the use of Python 2.4 or later. If compatibility
with old versions is needed, use the latter solution.
The need for this feature was suggested by Cem Karan.
09/14/06: beazley
Support for single-character literal tokens has been added to yacc.
These literals must be enclosed in quotes. For example:
def p_expr(p):
"expr : expr '+' expr"
...
def p_expr(p):
'expr : expr "-" expr'
...
In addition to this, it is necessary to tell the lexer module about
literal characters. This is done by defining the variable 'literals'
as a list of characters. This should be defined in the module that
invokes the lex.lex() function. For example:
literals = ['+','-','*','/','(',')','=']
or simply
literals = '+=*/()='
It is important to note that literals can only be a single character.
When the lexer fails to match a token using its normal regular expression
rules, it will check the current character against the literal list.
If found, it will be returned with a token type set to match the literal
character. Otherwise, an illegal character will be signalled.
09/14/06: beazley
Modified PLY to install itself as a proper Python package called 'ply'.
This will make it a little more friendly to other modules. This
changes the usage of PLY only slightly. Just do this to import the
modules
import ply.lex as lex
import ply.yacc as yacc
Alternatively, you can do this:
from ply import *
Which imports both the lex and yacc modules.
Change suggested by Lee June.
09/13/06: beazley
Changed the handling of negative indices when used in production rules.
A negative production index now accesses already parsed symbols on the
parsing stack. For example,
def p_foo(p):
"foo: A B C D"
print p[1] # Value of 'A' symbol
print p[2] # Value of 'B' symbol
print p[-1] # Value of whatever symbol appears before A
# on the parsing stack.
p[0] = some_val # Sets the value of the 'foo' grammer symbol
This behavior makes it easier to work with embedded actions within the
parsing rules. For example, in C-yacc, it is possible to write code like
this:
bar: A { printf("seen an A = %d\n", $1); } B { do_stuff; }
In this example, the printf() code executes immediately after A has been
parsed. Within the embedded action code, $1 refers to the A symbol on
the stack.
To perform this equivalent action in PLY, you need to write a pair
of rules like this:
def p_bar(p):
"bar : A seen_A B"
do_stuff
def p_seen_A(p):
"seen_A :"
print "seen an A =", p[-1]
The second rule "seen_A" is merely a empty production which should be
reduced as soon as A is parsed in the "bar" rule above. The use
of the negative index p[-1] is used to access whatever symbol appeared
before the seen_A symbol.
This feature also makes it possible to support inherited attributes.
For example:
def p_decl(p):
"decl : scope name"
def p_scope(p):
"""scope : GLOBAL
| LOCAL"""
p[0] = p[1]
def p_name(p):
"name : ID"
if p[-1] == "GLOBAL":
# ...
else if p[-1] == "LOCAL":
#...
In this case, the name rule is inheriting an attribute from the
scope declaration that precedes it.
*** POTENTIAL INCOMPATIBILITY ***
If you are currently using negative indices within existing grammar rules,
your code will break. This should be extremely rare if non-existent in
most cases. The argument to various grammar rules is not usually not
processed in the same way as a list of items.
Version 2.0
------------------------------
09/07/06: beazley
Major cleanup and refactoring of the LR table generation code. Both SLR
and LALR(1) table generation is now performed by the same code base with
only minor extensions for extra LALR(1) processing.
09/07/06: beazley
Completely reimplemented the entire LALR(1) parsing engine to use the
DeRemer and Pennello algorithm for calculating lookahead sets. This
significantly improves the performance of generating LALR(1) tables
and has the added feature of actually working correctly! If you
experienced weird behavior with LALR(1) in prior releases, this should
hopefully resolve all of those problems. Many thanks to
Andrew Waters and Markus Schoepflin for submitting bug reports
and helping me test out the revised LALR(1) support.
Version 1.8
------------------------------
08/02/06: beazley
Fixed a problem related to the handling of default actions in LALR(1)
parsing. If you experienced subtle and/or bizarre behavior when trying
to use the LALR(1) engine, this may correct those problems. Patch
contributed by Russ Cox. Note: This patch has been superceded by
revisions for LALR(1) parsing in Ply-2.0.
08/02/06: beazley
Added support for slicing of productions in yacc.
Patch contributed by Patrick Mezard.
Version 1.7
------------------------------
03/02/06: beazley
Fixed infinite recursion problem ReduceToTerminals() function that
would sometimes come up in LALR(1) table generation. Reported by
Markus Schoepflin.
03/01/06: beazley
Added "reflags" argument to lex(). For example:
lex.lex(reflags=re.UNICODE)
This can be used to specify optional flags to the re.compile() function
used inside the lexer. This may be necessary for special situations such
as processing Unicode (e.g., if you want escapes like \w and \b to consult
the Unicode character property database). The need for this suggested by
Andreas Jung.
03/01/06: beazley
Fixed a bug with an uninitialized variable on repeated instantiations of parser
objects when the write_tables=0 argument was used. Reported by Michael Brown.
03/01/06: beazley
Modified lex.py to accept Unicode strings both as the regular expressions for
tokens and as input. Hopefully this is the only change needed for Unicode support.
Patch contributed by Johan Dahl.
03/01/06: beazley
Modified the class-based interface to work with new-style or old-style classes.
Patch contributed by Michael Brown (although I tweaked it slightly so it would work
with older versions of Python).
Version 1.6
------------------------------
05/27/05: beazley
Incorporated patch contributed by Christopher Stawarz to fix an extremely
devious bug in LALR(1) parser generation. This patch should fix problems
numerous people reported with LALR parsing.
05/27/05: beazley
Fixed problem with lex.py copy constructor. Reported by Dave Aitel, Aaron Lav,
and Thad Austin.
05/27/05: beazley
Added outputdir option to yacc() to control output directory. Contributed
by Christopher Stawarz.
05/27/05: beazley
Added rununit.py test script to run tests using the Python unittest module.
Contributed by Miki Tebeka.
Version 1.5
------------------------------
05/26/04: beazley
Major enhancement. LALR(1) parsing support is now working.
This feature was implemented by Elias Ioup (ezioup@alumni.uchicago.edu)
and optimized by David Beazley. To use LALR(1) parsing do
the following:
yacc.yacc(method="LALR")
Computing LALR(1) parsing tables takes about twice as long as
the default SLR method. However, LALR(1) allows you to handle
more complex grammars. For example, the ANSI C grammar
(in example/ansic) has 13 shift-reduce conflicts with SLR, but
only has 1 shift-reduce conflict with LALR(1).
05/20/04: beazley
Added a __len__ method to parser production lists. Can
be used in parser rules like this:
def p_somerule(p):
"""a : B C D
| E F"
if (len(p) == 3):
# Must have been first rule
elif (len(p) == 2):
# Must be second rule
Suggested by Joshua Gerth and others.
Version 1.4
------------------------------
04/23/04: beazley
Incorporated a variety of patches contributed by Eric Raymond.
These include:
0. Cleans up some comments so they don't wrap on an 80-column display.
1. Directs compiler errors to stderr where they belong.
2. Implements and documents automatic line counting when \n is ignored.
3. Changes the way progress messages are dumped when debugging is on.
The new format is both less verbose and conveys more information than
the old, including shift and reduce actions.
04/23/04: beazley
Added a Python setup.py file to simply installation. Contributed
by Adam Kerrison.
04/23/04: beazley
Added patches contributed by Adam Kerrison.
- Some output is now only shown when debugging is enabled. This
means that PLY will be completely silent when not in debugging mode.
- An optional parameter "write_tables" can be passed to yacc() to
control whether or not parsing tables are written. By default,
it is true, but it can be turned off if you don't want the yacc
table file. Note: disabling this will cause yacc() to regenerate
the parsing table each time.
04/23/04: beazley
Added patches contributed by David McNab. This patch addes two
features:
- The parser can be supplied as a class instead of a module.
For an example of this, see the example/classcalc directory.
- Debugging output can be directed to a filename of the user's
choice. Use
yacc(debugfile="somefile.out")
Version 1.3
------------------------------
12/10/02: jmdyck

147
ext/ply/README
View file

@ -1,14 +1,8 @@
PLY (Python Lex-Yacc) Version 1.2 (November 27, 2002)
PLY (Python Lex-Yacc) Version 2.3 (February 18, 2007)
David M. Beazley
Department of Computer Science
University of Chicago
Chicago, IL 60637
beazley@cs.uchicago.edu
David M. Beazley (dave@dabeaz.com)
Copyright (C) 2001 David M. Beazley
$Header: /home/stever/bk/newmem2/ext/ply/README 1.1 03/06/06 14:53:34-00:00 stever@ $
Copyright (C) 2001-2007 David M. Beazley
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
@ -52,11 +46,10 @@ Python, there are several reasons why you might want to consider PLY:
Currently, PLY builds its parsing tables using the SLR algorithm which
is slightly weaker than LALR(1) used in traditional yacc.
- Like John Aycock's excellent SPARK toolkit, PLY uses Python
reflection to build lexers and parsers. This greatly simplifies
the task of parser construction since it reduces the number of files
and eliminates the need to run a separate lex/yacc tool before
running your program.
- PLY uses Python introspection features to build lexers and parsers.
This greatly simplifies the task of parser construction since it reduces
the number of files and eliminates the need to run a separate lex/yacc
tool before running your program.
- PLY can be used to build parsers for "real" programming languages.
Although it is not ultra-fast due to its Python implementation,
@ -77,51 +70,79 @@ common usability problems.
How to Use
==========
PLY consists of two files : lex.py and yacc.py. To use the system,
simply copy these files to your project and import them like standard
Python modules.
PLY consists of two files : lex.py and yacc.py. These are contained
within the 'ply' directory which may also be used as a Python package.
To use PLY, simply copy the 'ply' directory to your project and import
lex and yacc from the associated 'ply' package. For example:
import ply.lex as lex
import ply.yacc as yacc
Alternatively, you can copy just the files lex.py and yacc.py
individually and use them as modules. For example:
import lex
import yacc
The file setup.py can be used to install ply using distutils.
The file doc/ply.html contains complete documentation on how to use
the system.
The example directory contains several different examples including a
PLY specification for ANSI C as given in K&R 2nd Ed. Note: To use
the examples, you will need to copy the lex.py and yacc.py files to
the example directory.
PLY specification for ANSI C as given in K&R 2nd Ed.
A simple example is found at the end of this document
Requirements
============
PLY requires the use of Python 2.0 or greater. It should work on
just about any platform.
PLY requires the use of Python 2.1 or greater. However, you should
use the latest Python release if possible. It should work on just
about any platform. PLY has been tested with both CPython and Jython.
However, it does not seem to work with IronPython.
Resources
=========
More information about PLY can be obtained on the PLY webpage at:
http://systems.cs.uchicago.edu/ply
http://www.dabeaz.com/ply
For a detailed overview of parsing theory, consult the excellent
book "Compilers : Principles, Techniques, and Tools" by Aho, Sethi, and
Ullman. The topics found in "Lex & Yacc" by Levine, Mason, and Brown
may also be useful.
Given that this is the first release, I welcome your comments on how
to improve the current implementation. See the TODO file for things that
still need to be done.
A Google group for PLY can be found at
http://groups.google.com/group/ply-hack
Acknowledgments
===============
A special thanks is in order for all of the students in CS326 who
suffered through about 25 different versions of these tools :-).
The CHANGES file acknowledges those who have contributed patches.
Elias Ioup did the first implementation of LALR(1) parsing in PLY-1.x.
Andrew Waters and Markus Schoepflin were instrumental in reporting bugs
and testing a revised LALR(1) implementation for PLY-2.0.
Special Note for PLY-2.x
========================
PLY-2.0 is the first in a series of PLY releases that will be adding a
variety of significant new features. The first release in this series
(Ply-2.0) should be 100% compatible with all previous Ply-1.x releases
except for the fact that Ply-2.0 features a correct implementation of
LALR(1) table generation.
If you have suggestions for improving PLY in future 2.x releases, please
contact me. - Dave
Example
=======
Here is a simple example showing a PLY implementation of a calculator with variables.
Here is a simple example showing a PLY implementation of a calculator
with variables.
# -----------------------------------------------------------------------------
# calc.py
@ -160,14 +181,14 @@ t_ignore = " \t"
def t_newline(t):
r'\n+'
t.lineno += t.value.count("\n")
t.lexer.lineno += t.value.count("\n")
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.skip(1)
t.lexer.skip(1)
# Build the lexer
import lex
import ply.lex as lex
lex.lex()
# Precedence rules for the arithmetic operators
@ -180,48 +201,48 @@ precedence = (
# dictionary of names (for storing variables)
names = { }
def p_statement_assign(t):
def p_statement_assign(p):
'statement : NAME EQUALS expression'
names[t[1]] = t[3]
names[p[1]] = p[3]
def p_statement_expr(t):
def p_statement_expr(p):
'statement : expression'
print t[1]
print p[1]
def p_expression_binop(t):
def p_expression_binop(p):
'''expression : expression PLUS expression
| expression MINUS expression
| expression TIMES expression
| expression DIVIDE expression'''
if t[2] == '+' : t[0] = t[1] + t[3]
elif t[2] == '-': t[0] = t[1] - t[3]
elif t[2] == '*': t[0] = t[1] * t[3]
elif t[2] == '/': t[0] = t[1] / t[3]
if p[2] == '+' : p[0] = p[1] + p[3]
elif p[2] == '-': p[0] = p[1] - p[3]
elif p[2] == '*': p[0] = p[1] * p[3]
elif p[2] == '/': p[0] = p[1] / p[3]
def p_expression_uminus(t):
def p_expression_uminus(p):
'expression : MINUS expression %prec UMINUS'
t[0] = -t[2]
p[0] = -p[2]
def p_expression_group(t):
def p_expression_group(p):
'expression : LPAREN expression RPAREN'
t[0] = t[2]
p[0] = p[2]
def p_expression_number(t):
def p_expression_number(p):
'expression : NUMBER'
t[0] = t[1]
p[0] = p[1]
def p_expression_name(t):
def p_expression_name(p):
'expression : NAME'
try:
t[0] = names[t[1]]
p[0] = names[p[1]]
except LookupError:
print "Undefined name '%s'" % t[1]
t[0] = 0
print "Undefined name '%s'" % p[1]
p[0] = 0
def p_error(t):
print "Syntax error at '%s'" % t.value
def p_error(p):
print "Syntax error at '%s'" % p.value
import yacc
import ply.yacc as yacc
yacc.yacc()
while 1:
@ -232,13 +253,21 @@ while 1:
yacc.parse(s)
Bug Reports and Patches
=======================
Because of the extremely specialized and advanced nature of PLY, I
rarely spend much time working on it unless I receive very specific
bug-reports and/or patches to fix problems. I also try to incorporate
submitted feature requests and enhancements into each new version. To
contact me about bugs and/or new features, please send email to
dave@dabeaz.com.
In addition there is a Google group for discussing PLY related issues at
http://groups.google.com/group/ply-hack
-- Dave

18
ext/ply/TODO
View file

@ -1,22 +1,14 @@
The PLY to-do list:
$Header: /home/stever/bk/newmem2/ext/ply/TODO 1.1 03/06/06 14:53:34-00:00 stever@ $
1. More interesting parsing examples.
1. Create a Python package using distutils
2. More interesting parsing examples.
3. Work on the ANSI C grammar so that it can actually parse C programs. To do this,
2. Work on the ANSI C grammar so that it can actually parse C programs. To do this,
some extra code needs to be added to the lexer to deal with typedef names and enumeration
constants.
4. Get LALR(1) to work. Hard, but not impossible.
3. More tests in the test directory.
5. More tests in the test directory.
4. Performance improvements and cleanup in yacc.py.
6. Performance improvements and cleanup in yacc.py.
7. More documentation.
8. Lots and lots of cleanup.
5. More documentation (?).

194
ext/ply/doc/makedoc.py Normal file
View file

@ -0,0 +1,194 @@
#!/usr/local/bin/python
###############################################################################
# Takes a chapter as input and adds internal links and numbering to all
# of the H1, H2, H3, H4 and H5 sections.
#
# Every heading HTML tag (H1, H2 etc) is given an autogenerated name to link
# to. However, if the name is not an autogenerated name from a previous run,
# it will be kept. If it is autogenerated, it might change on subsequent runs
# of this program. Thus if you want to create links to one of the headings,
# then change the heading link name to something that does not look like an
# autogenerated link name.
###############################################################################
import sys
import re
import string
###############################################################################
# Functions
###############################################################################
# Regexs for <a name="..."></a>
alink = re.compile(r"<a *name *= *\"(.*)\"></a>", re.IGNORECASE)
heading = re.compile(r"(_nn\d)", re.IGNORECASE)
def getheadingname(m):
autogeneratedheading = True;
if m.group(1) != None:
amatch = alink.match(m.group(1))
if amatch:
# A non-autogenerated heading - keep it
headingname = amatch.group(1)
autogeneratedheading = heading.match(headingname)
if autogeneratedheading:
# The heading name was either non-existent or autogenerated,
# We can create a new heading / change the existing heading
headingname = "%s_nn%d" % (filenamebase, nameindex)
return headingname
###############################################################################
# Main program
###############################################################################
if len(sys.argv) != 2:
print "usage: makedoc.py filename"
sys.exit(1)
filename = sys.argv[1]
filenamebase = string.split(filename,".")[0]
section = 0
subsection = 0
subsubsection = 0
subsubsubsection = 0
nameindex = 0
name = ""
# Regexs for <h1>,... <h5> sections
h1 = re.compile(r".*?<H1>(<a.*a>)*[\d\.\s]*(.*?)</H1>", re.IGNORECASE)
h2 = re.compile(r".*?<H2>(<a.*a>)*[\d\.\s]*(.*?)</H2>", re.IGNORECASE)
h3 = re.compile(r".*?<H3>(<a.*a>)*[\d\.\s]*(.*?)</H3>", re.IGNORECASE)
h4 = re.compile(r".*?<H4>(<a.*a>)*[\d\.\s]*(.*?)</H4>", re.IGNORECASE)
h5 = re.compile(r".*?<H5>(<a.*a>)*[\d\.\s]*(.*?)</H5>", re.IGNORECASE)
data = open(filename).read() # Read data
open(filename+".bak","w").write(data) # Make backup
lines = data.splitlines()
result = [ ] # This is the result of postprocessing the file
index = "<!-- INDEX -->\n<div class=\"sectiontoc\">\n" # index contains the index for adding at the top of the file. Also printed to stdout.
skip = 0
skipspace = 0
for s in lines:
if s == "<!-- INDEX -->":
if not skip:
result.append("@INDEX@")
skip = 1
else:
skip = 0
continue;
if skip:
continue
if not s and skipspace:
continue
if skipspace:
result.append("")
result.append("")
skipspace = 0
m = h2.match(s)
if m:
prevheadingtext = m.group(2)
nameindex += 1
section += 1
headingname = getheadingname(m)
result.append("""<H2><a name="%s"></a>%d. %s</H2>""" % (headingname,section, prevheadingtext))
if subsubsubsection:
index += "</ul>\n"
if subsubsection:
index += "</ul>\n"
if subsection:
index += "</ul>\n"
if section == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
subsection = 0
subsubsection = 0
subsubsubsection = 0
skipspace = 1
continue
m = h3.match(s)
if m:
prevheadingtext = m.group(2)
nameindex += 1
subsection += 1
headingname = getheadingname(m)
result.append("""<H3><a name="%s"></a>%d.%d %s</H3>""" % (headingname,section, subsection, prevheadingtext))
if subsubsubsection:
index += "</ul>\n"
if subsubsection:
index += "</ul>\n"
if subsection == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
subsubsection = 0
skipspace = 1
continue
m = h4.match(s)
if m:
prevheadingtext = m.group(2)
nameindex += 1
subsubsection += 1
subsubsubsection = 0
headingname = getheadingname(m)
result.append("""<H4><a name="%s"></a>%d.%d.%d %s</H4>""" % (headingname,section, subsection, subsubsection, prevheadingtext))
if subsubsubsection:
index += "</ul>\n"
if subsubsection == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
skipspace = 1
continue
m = h5.match(s)
if m:
prevheadingtext = m.group(2)
nameindex += 1
subsubsubsection += 1
headingname = getheadingname(m)
result.append("""<H5><a name="%s"></a>%d.%d.%d.%d %s</H5>""" % (headingname,section, subsection, subsubsection, subsubsubsection, prevheadingtext))
if subsubsubsection == 1:
index += "<ul>\n"
index += """<li><a href="#%s">%s</a>\n""" % (headingname,prevheadingtext)
skipspace = 1
continue
result.append(s)
if subsubsubsection:
index += "</ul>\n"
if subsubsection:
index += "</ul>\n"
if subsection:
index += "</ul>\n"
if section:
index += "</ul>\n"
index += "</div>\n<!-- INDEX -->\n"
data = "\n".join(result)
data = data.replace("@INDEX@",index) + "\n";
# Write the file back out
open(filename,"w").write(data)

1880
ext/ply/doc/ply.html
View file

File diff suppressed because it is too large Load diff

79
ext/ply/example/BASIC/README Normal file
View file

@ -0,0 +1,79 @@
Inspired by a September 14, 2006 Salon article "Why Johnny Can't Code" by
David Brin (http://www.salon.com/tech/feature/2006/09/14/basic/index.html),
I thought that a fully working BASIC interpreter might be an interesting,
if not questionable, PLY example. Uh, okay, so maybe it's just a bad idea,
but in any case, here it is.
In this example, you'll find a rough implementation of 1964 Dartmouth BASIC
as described in the manual at:
http://www.bitsavers.org/pdf/dartmouth/BASIC_Oct64.pdf
See also:
http://en.wikipedia.org/wiki/Dartmouth_BASIC
This dialect is downright primitive---there are no string variables
and no facilities for interactive input. Moreover, subroutines and functions
are brain-dead even more than they usually are for BASIC. Of course,
the GOTO statement is provided.
Nevertheless, there are a few interesting aspects of this example:
- It illustrates a fully working interpreter including lexing, parsing,
and interpretation of instructions.
- The parser shows how to catch and report various kinds of parsing
errors in a more graceful way.
- The example both parses files (supplied on command line) and
interactive input entered line by line.
- It shows how you might represent parsed information. In this case,
each BASIC statement is encoded into a Python tuple containing the
statement type and parameters. These tuples are then stored in
a dictionary indexed by program line numbers.
- Even though it's just BASIC, the parser contains more than 80
rules and 150 parsing states. Thus, it's a little more meaty than
the calculator example.
To use the example, run it as follows:
% python basic.py hello.bas
HELLO WORLD
%
or use it interactively:
% python basic.py
[BASIC] 10 PRINT "HELLO WORLD"
[BASIC] 20 END
[BASIC] RUN
HELLO WORLD
[BASIC]
The following files are defined:
basic.py - High level script that controls everything
basiclex.py - BASIC tokenizer
basparse.py - BASIC parser
basinterp.py - BASIC interpreter that runs parsed programs.
In addition, a number of sample BASIC programs (.bas suffix) are
provided. These were taken out of the Dartmouth manual.
Disclaimer: I haven't spent a ton of time testing this and it's likely that
I've skimped here and there on a few finer details (e.g., strictly enforcing
variable naming rules). However, the interpreter seems to be able to run
the examples in the BASIC manual.
Have fun!
-Dave

68
ext/ply/example/BASIC/basic.py Normal file
View file

@ -0,0 +1,68 @@
# An implementation of Dartmouth BASIC (1964)
#
import sys
sys.path.insert(0,"../..")
import basiclex
import basparse
import basinterp
# If a filename has been specified, we try to run it.
# If a runtime error occurs, we bail out and enter
# interactive mode below
if len(sys.argv) == 2:
data = open(sys.argv[1]).read()
prog = basparse.parse(data)
if not prog: raise SystemExit
b = basinterp.BasicInterpreter(prog)
try:
b.run()
raise SystemExit
except RuntimeError:
pass
else:
b = basinterp.BasicInterpreter({})
# Interactive mode. This incrementally adds/deletes statements
# from the program stored in the BasicInterpreter object. In
# addition, special commands 'NEW','LIST',and 'RUN' are added.
# Specifying a line number with no code deletes that line from
# the program.
while 1:
try:
line = raw_input("[BASIC] ")
except EOFError:
raise SystemExit
if not line: continue
line += "\n"
prog = basparse.parse(line)
if not prog: continue
keys = prog.keys()
if keys[0] > 0:
b.add_statements(prog)
else:
stat = prog[keys[0]]
if stat[0] == 'RUN':
try:
b.run()
except RuntimeError:
pass
elif stat[0] == 'LIST':
b.list()
elif stat[0] == 'BLANK':
b.del_line(stat[1])
elif stat[0] == 'NEW':
b.new()

74
ext/ply/example/BASIC/basiclex.py Normal file
View file

@ -0,0 +1,74 @@
# An implementation of Dartmouth BASIC (1964)
from ply import *
keywords = (
'LET','READ','DATA','PRINT','GOTO','IF','THEN','FOR','NEXT','TO','STEP',
'END','STOP','DEF','GOSUB','DIM','REM','RETURN','RUN','LIST','NEW',
)
tokens = keywords + (
'EQUALS','PLUS','MINUS','TIMES','DIVIDE','POWER',
'LPAREN','RPAREN','LT','LE','GT','GE','NE',
'COMMA','SEMI', 'INTEGER','FLOAT', 'STRING',
'ID','NEWLINE'
)
t_ignore = ' \t'
def t_REM(t):
r'REM .*'
return t
def t_ID(t):
r'[A-Z][A-Z0-9]*'
if t.value in keywords:
t.type = t.value
return t
t_EQUALS = r'='
t_PLUS = r'\+'
t_MINUS = r'-'
t_TIMES = r'\*'
t_POWER = r'\^'
t_DIVIDE = r'/'
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_LT = r'<'
t_LE = r'<='
t_GT = r'>'
t_GE = r'>='
t_NE = r'<>'
t_COMMA = r'\,'
t_SEMI = r';'
t_INTEGER = r'\d+'
t_FLOAT = r'((\d*\.\d+)(E[\+-]?\d+)?|([1-9]\d*E[\+-]?\d+))'
t_STRING = r'\".*?\"'
def t_NEWLINE(t):
r'\n'
t.lexer.lineno += 1
return t
def t_error(t):
print "Illegal character", t.value[0]
t.lexer.skip(1)
lex.lex()

440
ext/ply/example/BASIC/basinterp.py Normal file
View file

@ -0,0 +1,440 @@
# This file provides the runtime support for running a basic program
# Assumes the program has been parsed using basparse.py
import sys
import math
import random
class BasicInterpreter:
# Initialize the interpreter. prog is a dictionary
# containing (line,statement) mappings
def __init__(self,prog):
self.prog = prog
self.functions = { # Built-in function table
'SIN' : lambda z: math.sin(self.eval(z)),
'COS' : lambda z: math.cos(self.eval(z)),
'TAN' : lambda z: math.tan(self.eval(z)),
'ATN' : lambda z: math.atan(self.eval(z)),
'EXP' : lambda z: math.exp(self.eval(z)),
'ABS' : lambda z: abs(self.eval(z)),
'LOG' : lambda z: math.log(self.eval(z)),
'SQR' : lambda z: math.sqrt(self.eval(z)),
'INT' : lambda z: int(self.eval(z)),
'RND' : lambda z: random.random()
}
# Collect all data statements
def collect_data(self):
self.data = []
for lineno in self.stat:
if self.prog[lineno][0] == 'DATA':
self.data = self.data + self.prog[lineno][1]
self.dc = 0 # Initialize the data counter
# Check for end statements
def check_end(self):
has_end = 0
for lineno in self.stat:
if self.prog[lineno][0] == 'END' and not has_end:
has_end = lineno
if not has_end:
print "NO END INSTRUCTION"
self.error = 1
if has_end != lineno:
print "END IS NOT LAST"
self.error = 1
# Check loops
def check_loops(self):
for pc in range(len(self.stat)):
lineno = self.stat[pc]
if self.prog[lineno][0] == 'FOR':
forinst = self.prog[lineno]
loopvar = forinst[1]
for i in range(pc+1,len(self.stat)):
if self.prog[self.stat[i]][0] == 'NEXT':
nextvar = self.prog[self.stat[i]][1]
if nextvar != loopvar: continue
self.loopend[pc] = i
break
else:
print "FOR WITHOUT NEXT AT LINE" % self.stat[pc]
self.error = 1
# Evaluate an expression
def eval(self,expr):
etype = expr[0]
if etype == 'NUM': return expr[1]
elif etype == 'GROUP': return self.eval(expr[1])
elif etype == 'UNARY':
if expr[1] == '-': return -self.eval(expr[2])
elif etype == 'BINOP':
if expr[1] == '+': return self.eval(expr[2])+self.eval(expr[3])
elif expr[1] == '-': return self.eval(expr[2])-self.eval(expr[3])
elif expr[1] == '*': return self.eval(expr[2])*self.eval(expr[3])
elif expr[1] == '/': return float(self.eval(expr[2]))/self.eval(expr[3])
elif expr[1] == '^': return abs(self.eval(expr[2]))**self.eval(expr[3])
elif etype == 'VAR':
var,dim1,dim2 = expr[1]
if not dim1 and not dim2:
if self.vars.has_key(var):
return self.vars[var]
else:
print "UNDEFINED VARIABLE", var, "AT LINE", self.stat[self.pc]
raise RuntimeError
# May be a list lookup or a function evaluation
if dim1 and not dim2:
if self.functions.has_key(var):
# A function
return self.functions[var](dim1)
else:
# A list evaluation
if self.lists.has_key(var):
dim1val = self.eval(dim1)
if dim1val < 1 or dim1val > len(self.lists[var]):
print "LIST INDEX OUT OF BOUNDS AT LINE", self.stat[self.pc]
raise RuntimeError
return self.lists[var][dim1val-1]
if dim1 and dim2:
if self.tables.has_key(var):
dim1val = self.eval(dim1)
dim2val = self.eval(dim2)
if dim1val < 1 or dim1val > len(self.tables[var]) or dim2val < 1 or dim2val > len(self.tables[var][0]):
print "TABLE INDEX OUT OUT BOUNDS AT LINE", self.stat[self.pc]
raise RuntimeError
return self.tables[var][dim1val-1][dim2val-1]
print "UNDEFINED VARIABLE", var, "AT LINE", self.stat[self.pc]
raise RuntimeError
# Evaluate a relational expression
def releval(self,expr):
etype = expr[1]
lhs = self.eval(expr[2])
rhs = self.eval(expr[3])
if etype == '<':
if lhs < rhs: return 1
else: return 0
elif etype == '<=':
if lhs <= rhs: return 1
else: return 0
elif etype == '>':
if lhs > rhs: return 1
else: return 0
elif etype == '>=':
if lhs >= rhs: return 1
else: return 0
elif etype == '=':
if lhs == rhs: return 1
else: return 0
elif etype == '<>':
if lhs != rhs: return 1
else: return 0
# Assignment
def assign(self,target,value):
var, dim1, dim2 = target
if not dim1 and not dim2:
self.vars[var] = self.eval(value)
elif dim1 and not dim2:
# List assignment
dim1val = self.eval(dim1)
if not self.lists.has_key(var):
self.lists[var] = [0]*10
if dim1val > len(self.lists[var]):
print "DIMENSION TOO LARGE AT LINE", self.stat[self.pc]
raise RuntimeError
self.lists[var][dim1val-1] = self.eval(value)
elif dim1 and dim2:
dim1val = self.eval(dim1)
dim2val = self.eval(dim2)
if not self.tables.has_key(var):
temp = [0]*10
v = []
for i in range(10): v.append(temp[:])
self.tables[var] = v
# Variable already exists
if dim1val > len(self.tables[var]) or dim2val > len(self.tables[var][0]):
print "DIMENSION TOO LARGE AT LINE", self.stat[self.pc]
raise RuntimeError
self.tables[var][dim1val-1][dim2val-1] = self.eval(value)
# Change the current line number
def goto(self,linenum):
if not self.prog.has_key(linenum):
print "UNDEFINED LINE NUMBER %d AT LINE %d" % (linenum, self.stat[self.pc])
raise RuntimeError
self.pc = self.stat.index(linenum)
# Run it
def run(self):
self.vars = { } # All variables
self.lists = { } # List variables
self.tables = { } # Tables
self.loops = [ ] # Currently active loops
self.loopend= { } # Mapping saying where loops end
self.gosub = None # Gosub return point (if any)
self.error = 0 # Indicates program error
self.stat = self.prog.keys() # Ordered list of all line numbers
self.stat.sort()
self.pc = 0 # Current program counter
# Processing prior to running
self.collect_data() # Collect all of the data statements
self.check_end()
self.check_loops()
if self.error: raise RuntimeError
while 1:
line = self.stat[self.pc]
instr = self.prog[line]
op = instr[0]
# END and STOP statements
if op == 'END' or op == 'STOP':
break # We're done
# GOTO statement
elif op == 'GOTO':
newline = instr[1]
self.goto(newline)
continue
# PRINT statement
elif op == 'PRINT':
plist = instr[1]
out = ""
for label,val in plist:
if out:
out += ' '*(15 - (len(out) % 15))
out += label
if val:
if label: out += " "
eval = self.eval(val)
out += str(eval)
sys.stdout.write(out)
end = instr[2]
if not (end == ',' or end == ';'):
sys.stdout.write("\n")
if end == ',': sys.stdout.write(" "*(15-(len(out) % 15)))
if end == ';': sys.stdout.write(" "*(3-(len(out) % 3)))
# LET statement
elif op == 'LET':
target = instr[1]
value = instr[2]
self.assign(target,value)
# READ statement
elif op == 'READ':
for target in instr[1]:
if self.dc < len(self.data):
value = ('NUM',self.data[self.dc])
self.assign(target,value)
self.dc += 1
else:
# No more data. Program ends
return
elif op == 'IF':
relop = instr[1]
newline = instr[2]
if (self.releval(relop)):
self.goto(newline)
continue
elif op == 'FOR':
loopvar = instr[1]
initval = instr[2]
finval = instr[3]
stepval = instr[4]
# Check to see if this is a new loop
if not self.loops or self.loops[-1][0] != self.pc:
# Looks like a new loop. Make the initial assignment
newvalue = initval
self.assign((loopvar,None,None),initval)
if not stepval: stepval = ('NUM',1)
stepval = self.eval(stepval) # Evaluate step here
self.loops.append((self.pc,stepval))
else:
# It's a repeat of the previous loop
# Update the value of the loop variable according to the step
stepval = ('NUM',self.loops[-1][1])
newvalue = ('BINOP','+',('VAR',(loopvar,None,None)),stepval)
if self.loops[-1][1] < 0: relop = '>='
else: relop = '<='
if not self.releval(('RELOP',relop,newvalue,finval)):
# Loop is done. Jump to the NEXT
self.pc = self.loopend[self.pc]
self.loops.pop()
else:
self.assign((loopvar,None,None),newvalue)
elif op == 'NEXT':
if not self.loops:
print "NEXT WITHOUT FOR AT LINE",line
return
nextvar = instr[1]
self.pc = self.loops[-1][0]
loopinst = self.prog[self.stat[self.pc]]
forvar = loopinst[1]
if nextvar != forvar:
print "NEXT DOESN'T MATCH FOR AT LINE", line
return
continue
elif op == 'GOSUB':
newline = instr[1]
if self.gosub:
print "ALREADY IN A SUBROUTINE AT LINE", line
return
self.gosub = self.stat[self.pc]
self.goto(newline)
continue
elif op == 'RETURN':
if not self.gosub:
print "RETURN WITHOUT A GOSUB AT LINE",line
return
self.goto(self.gosub)
self.gosub = None
elif op == 'FUNC':
fname = instr[1]
pname = instr[2]
expr = instr[3]
def eval_func(pvalue,name=pname,self=self,expr=expr):
self.assign((pname,None,None),pvalue)
return self.eval(expr)
self.functions[fname] = eval_func
elif op == 'DIM':
for vname,x,y in instr[1]:
if y == 0:
# Single dimension variable
self.lists[vname] = [0]*x
else:
# Double dimension variable
temp = [0]*y
v = []
for i in range(x):
v.append(temp[:])
self.tables[vname] = v
self.pc += 1
# Utility functions for program listing
def expr_str(self,expr):
etype = expr[0]
if etype == 'NUM': return str(expr[1])
elif etype == 'GROUP': return "(%s)" % self.expr_str(expr[1])
elif etype == 'UNARY':
if expr[1] == '-': return "-"+str(expr[2])
elif etype == 'BINOP':
return "%s %s %s" % (self.expr_str(expr[2]),expr[1],self.expr_str(expr[3]))
elif etype == 'VAR':
return self.var_str(expr[1])
def relexpr_str(self,expr):
return "%s %s %s" % (self.expr_str(expr[2]),expr[1],self.expr_str(expr[3]))
def var_str(self,var):
varname,dim1,dim2 = var
if not dim1 and not dim2: return varname
if dim1 and not dim2: return "%s(%s)" % (varname, self.expr_str(dim1))
return "%s(%s,%s)" % (varname, self.expr_str(dim1),self.expr_str(dim2))
# Create a program listing
def list(self):
stat = self.prog.keys() # Ordered list of all line numbers
stat.sort()
for line in stat:
instr = self.prog[line]
op = instr[0]
if op in ['END','STOP','RETURN']:
print line, op
continue
elif op == 'REM':
print line, instr[1]
elif op == 'PRINT':
print line, op,
first = 1
for p in instr[1]:
if not first: print ",",
if p[0] and p[1]: print '"%s"%s' % (p[0],self.expr_str(p[1])),
elif p[1]: print self.expr_str(p[1]),
else: print '"%s"' % (p[0],),
first = 0
if instr[2]: print instr[2]
else: print
elif op == 'LET':
print line,"LET",self.var_str(instr[1]),"=",self.expr_str(instr[2])
elif op == 'READ':
print line,"READ",
first = 1
for r in instr[1]:
if not first: print ",",
print self.var_str(r),
first = 0
print ""
elif op == 'IF':
print line,"IF %s THEN %d" % (self.relexpr_str(instr[1]),instr[2])
elif op == 'GOTO' or op == 'GOSUB':
print line, op, instr[1]
elif op == 'FOR':
print line,"FOR %s = %s TO %s" % (instr[1],self.expr_str(instr[2]),self.expr_str(instr[3])),
if instr[4]: print "STEP %s" % (self.expr_str(instr[4])),
print
elif op == 'NEXT':
print line,"NEXT", instr[1]
elif op == 'FUNC':
print line,"DEF %s(%s) = %s" % (instr[1],instr[2],self.expr_str(instr[3]))
elif op == 'DIM':
print line,"DIM",
first = 1
for vname,x,y in instr[1]:
if not first: print ",",
first = 0
if y == 0:
print "%s(%d)" % (vname,x),
else:
print "%s(%d,%d)" % (vname,x,y),
print
elif op == 'DATA':
print line,"DATA",
first = 1
for v in instr[1]:
if not first: print ",",
first = 0
print v,
print
# Erase the current program
def new(self):
self.prog = {}
# Insert statements
def add_statements(self,prog):
for line,stat in prog.items():
self.prog[line] = stat
# Delete a statement
def del_line(self,lineno):
try:
del self.prog[lineno]
except KeyError:
pass

424
ext/ply/example/BASIC/basparse.py Normal file
View file

@ -0,0 +1,424 @@
# An implementation of Dartmouth BASIC (1964)
#
from ply import *
import basiclex
tokens = basiclex.tokens
precedence = (
('left', 'PLUS','MINUS'),
('left', 'TIMES','DIVIDE'),
('left', 'POWER'),
('right','UMINUS')
)
#### A BASIC program is a series of statements. We represent the program as a
#### dictionary of tuples indexed by line number.
def p_program(p):
'''program : program statement
| statement'''
if len(p) == 2 and p[1]:
p[0] = { }
line,stat = p[1]
p[0][line] = stat
elif len(p) ==3:
p[0] = p[1]
if not p[0]: p[0] = { }
if p[2]:
line,stat = p[2]
p[0][line] = stat
#### This catch-all rule is used for any catastrophic errors. In this case,
#### we simply return nothing
def p_program_error(p):
'''program : error'''
p[0] = None
p.parser.error = 1
#### Format of all BASIC statements.
def p_statement(p):
'''statement : INTEGER command NEWLINE'''
if isinstance(p[2],str):
print p[2],"AT LINE", p[1]
p[0] = None
p.parser.error = 1
else:
lineno = int(p[1])
p[0] = (lineno,p[2])
#### Interactive statements.
def p_statement_interactive(p):
'''statement : RUN NEWLINE
| LIST NEWLINE
| NEW NEWLINE'''
p[0] = (0, (p[1],0))
#### Blank line number
def p_statement_blank(p):
'''statement : INTEGER NEWLINE'''
p[0] = (0,('BLANK',int(p[1])))
#### Error handling for malformed statements
def p_statement_bad(p):
'''statement : INTEGER error NEWLINE'''
print "MALFORMED STATEMENT AT LINE", p[1]
p[0] = None
p.parser.error = 1
#### Blank line
def p_statement_newline(p):
'''statement : NEWLINE'''
p[0] = None
#### LET statement
def p_command_let(p):
'''command : LET variable EQUALS expr'''
p[0] = ('LET',p[2],p[4])
def p_command_let_bad(p):
'''command : LET variable EQUALS error'''
p[0] = "BAD EXPRESSION IN LET"
#### READ statement
def p_command_read(p):
'''command : READ varlist'''
p[0] = ('READ',p[2])
def p_command_read_bad(p):
'''command : READ error'''
p[0] = "MALFORMED VARIABLE LIST IN READ"
#### DATA statement
def p_command_data(p):
'''command : DATA numlist'''
p[0] = ('DATA',p[2])
def p_command_data_bad(p):
'''command : DATA error'''
p[0] = "MALFORMED NUMBER LIST IN DATA"
#### PRINT statement
def p_command_print(p):
'''command : PRINT plist optend'''
p[0] = ('PRINT',p[2],p[3])
def p_command_print_bad(p):
'''command : PRINT error'''
p[0] = "MALFORMED PRINT STATEMENT"
#### Optional ending on PRINT. Either a comma (,) or semicolon (;)
def p_optend(p):
'''optend : COMMA
| SEMI
|'''
if len(p) == 2:
p[0] = p[1]
else:
p[0] = None
#### PRINT statement with no arguments
def p_command_print_empty(p):
'''command : PRINT'''
p[0] = ('PRINT',[],None)
#### GOTO statement
def p_command_goto(p):
'''command : GOTO INTEGER'''
p[0] = ('GOTO',int(p[2]))
def p_command_goto_bad(p):
'''command : GOTO error'''
p[0] = "INVALID LINE NUMBER IN GOTO"
#### IF-THEN statement
def p_command_if(p):
'''command : IF relexpr THEN INTEGER'''
p[0] = ('IF',p[2],int(p[4]))
def p_command_if_bad(p):
'''command : IF error THEN INTEGER'''
p[0] = "BAD RELATIONAL EXPRESSION"
def p_command_if_bad2(p):
'''command : IF relexpr THEN error'''
p[0] = "INVALID LINE NUMBER IN THEN"
#### FOR statement
def p_command_for(p):
'''command : FOR ID EQUALS expr TO expr optstep'''
p[0] = ('FOR',p[2],p[4],p[6],p[7])
def p_command_for_bad_initial(p):
'''command : FOR ID EQUALS error TO expr optstep'''
p[0] = "BAD INITIAL VALUE IN FOR STATEMENT"
def p_command_for_bad_final(p):
'''command : FOR ID EQUALS expr TO error optstep'''
p[0] = "BAD FINAL VALUE IN FOR STATEMENT"
def p_command_for_bad_step(p):
'''command : FOR ID EQUALS expr TO expr STEP error'''
p[0] = "MALFORMED STEP IN FOR STATEMENT"
#### Optional STEP qualifier on FOR statement
def p_optstep(p):
'''optstep : STEP expr
| empty'''
if len(p) == 3:
p[0] = p[2]
else:
p[0] = None
#### NEXT statement
def p_command_next(p):
'''command : NEXT ID'''
p[0] = ('NEXT',p[2])
def p_command_next_bad(p):
'''command : NEXT error'''
p[0] = "MALFORMED NEXT"
#### END statement
def p_command_end(p):
'''command : END'''
p[0] = ('END',)
#### REM statement
def p_command_rem(p):
'''command : REM'''
p[0] = ('REM',p[1])
#### STOP statement
def p_command_stop(p):
'''command : STOP'''
p[0] = ('STOP',)
#### DEF statement
def p_command_def(p):
'''command : DEF ID LPAREN ID RPAREN EQUALS expr'''
p[0] = ('FUNC',p[2],p[4],p[7])
def p_command_def_bad_rhs(p):
'''command : DEF ID LPAREN ID RPAREN EQUALS error'''
p[0] = "BAD EXPRESSION IN DEF STATEMENT"
def p_command_def_bad_arg(p):
'''command : DEF ID LPAREN error RPAREN EQUALS expr'''
p[0] = "BAD ARGUMENT IN DEF STATEMENT"
#### GOSUB statement
def p_command_gosub(p):
'''command : GOSUB INTEGER'''
p[0] = ('GOSUB',int(p[2]))
def p_command_gosub_bad(p):
'''command : GOSUB error'''
p[0] = "INVALID LINE NUMBER IN GOSUB"
#### RETURN statement
def p_command_return(p):
'''command : RETURN'''
p[0] = ('RETURN',)
#### DIM statement
def p_command_dim(p):
'''command : DIM dimlist'''
p[0] = ('DIM',p[2])
def p_command_dim_bad(p):
'''command : DIM error'''
p[0] = "MALFORMED VARIABLE LIST IN DIM"
#### List of variables supplied to DIM statement
def p_dimlist(p):
'''dimlist : dimlist COMMA dimitem
| dimitem'''
if len(p) == 4:
p[0] = p[1]
p[0].append(p[3])
else:
p[0] = [p[1]]
#### DIM items
def p_dimitem_single(p):
'''dimitem : ID LPAREN INTEGER RPAREN'''
p[0] = (p[1],eval(p[3]),0)
def p_dimitem_double(p):
'''dimitem : ID LPAREN INTEGER COMMA INTEGER RPAREN'''
p[0] = (p[1],eval(p[3]),eval(p[5]))
#### Arithmetic expressions
def p_expr_binary(p):
'''expr : expr PLUS expr
| expr MINUS expr
| expr TIMES expr
| expr DIVIDE expr
| expr POWER expr'''
p[0] = ('BINOP',p[2],p[1],p[3])
def p_expr_number(p):
'''expr : INTEGER
| FLOAT'''
p[0] = ('NUM',eval(p[1]))
def p_expr_variable(p):
'''expr : variable'''
p[0] = ('VAR',p[1])
def p_expr_group(p):
'''expr : LPAREN expr RPAREN'''
p[0] = ('GROUP',p[2])
def p_expr_unary(p):
'''expr : MINUS expr %prec UMINUS'''
p[0] = ('UNARY','-',p[2])
#### Relational expressions
def p_relexpr(p):
'''relexpr : expr LT expr
| expr LE expr
| expr GT expr
| expr GE expr
| expr EQUALS expr
| expr NE expr'''
p[0] = ('RELOP',p[2],p[1],p[3])
#### Variables
def p_variable(p):
'''variable : ID
| ID LPAREN expr RPAREN
| ID LPAREN expr COMMA expr RPAREN'''
if len(p) == 2:
p[0] = (p[1],None,None)
elif len(p) == 5:
p[0] = (p[1],p[3],None)
else:
p[0] = (p[1],p[3],p[5])
#### Builds a list of variable targets as a Python list
def p_varlist(p):
'''varlist : varlist COMMA variable
| variable'''
if len(p) > 2:
p[0] = p[1]
p[0].append(p[3])
else:
p[0] = [p[1]]
#### Builds a list of numbers as a Python list
def p_numlist(p):
'''numlist : numlist COMMA number
| number'''
if len(p) > 2:
p[0] = p[1]
p[0].append(p[3])
else:
p[0] = [p[1]]
#### A number. May be an integer or a float
def p_number(p):
'''number : INTEGER
| FLOAT'''
p[0] = eval(p[1])
#### A signed number.
def p_number_signed(p):
'''number : MINUS INTEGER
| MINUS FLOAT'''
p[0] = eval("-"+p[2])
#### List of targets for a print statement
#### Returns a list of tuples (label,expr)
def p_plist(p):
'''plist : plist COMMA pitem
| pitem'''
if len(p) > 3:
p[0] = p[1]
p[0].append(p[3])
else:
p[0] = [p[1]]
def p_item_string(p):
'''pitem : STRING'''
p[0] = (p[1][1:-1],None)
def p_item_string_expr(p):
'''pitem : STRING expr'''
p[0] = (p[1][1:-1],p[2])
def p_item_expr(p):
'''pitem : expr'''
p[0] = ("",p[1])
#### Empty
def p_empty(p):
'''empty : '''
#### Catastrophic error handler
def p_error(p):
if not p:
print "SYNTAX ERROR AT EOF"
bparser = yacc.yacc()
def parse(data):
bparser.error = 0
p = bparser.parse(data)
if bparser.error: return None
return p

14
ext/ply/example/BASIC/dim.bas Normal file
View file

@ -0,0 +1,14 @@
5 DIM A(50,15)
10 FOR I = 1 TO 50
20 FOR J = 1 TO 15
30 LET A(I,J) = I + J
35 REM PRINT I,J, A(I,J)
40 NEXT J
50 NEXT I
100 FOR I = 1 TO 50
110 FOR J = 1 TO 15
120 PRINT A(I,J),
130 NEXT J
140 PRINT
150 NEXT I
999 END

5
ext/ply/example/BASIC/func.bas Normal file
View file

@ -0,0 +1,5 @@
10 DEF FDX(X) = 2*X
20 FOR I = 0 TO 100
30 PRINT FDX(I)
40 NEXT I
50 END

22
ext/ply/example/BASIC/gcd.bas Normal file
View file

@ -0,0 +1,22 @@
10 PRINT "A","B","C","GCD"
20 READ A,B,C
30 LET X = A
40 LET Y = B
50 GOSUB 200
60 LET X = G
70 LET Y = C
80 GOSUB 200
90 PRINT A, B, C, G
100 GOTO 20
110 DATA 60, 90, 120
120 DATA 38456, 64872, 98765
130 DATA 32, 384, 72
200 LET Q = INT(X/Y)
210 LET R = X - Q*Y
220 IF R = 0 THEN 300
230 LET X = Y
240 LET Y = R
250 GOTO 200
300 LET G = Y
310 RETURN
999 END

13
ext/ply/example/BASIC/gosub.bas Normal file
View file

@ -0,0 +1,13 @@
100 LET X = 3
110 GOSUB 400
120 PRINT U, V, W
200 LET X = 5
210 GOSUB 400
220 LET Z = U + 2*V + 3*W
230 PRINT Z
240 GOTO 999
400 LET U = X*X
410 LET V = X*X*X
420 LET W = X*X*X*X + X*X*X + X*X + X
430 RETURN
999 END

4
ext/ply/example/BASIC/hello.bas Normal file
View file

@ -0,0 +1,4 @@
5 REM HELLO WORLD PROGAM
10 PRINT "HELLO WORLD"
99 END

17
ext/ply/example/BASIC/linear.bas Normal file
View file

@ -0,0 +1,17 @@
1 REM ::: SOLVE A SYSTEM OF LINEAR EQUATIONS
2 REM ::: A1*X1 + A2*X2 = B1
3 REM ::: A3*X1 + A4*X2 = B2
4 REM --------------------------------------
10 READ A1, A2, A3, A4
15 LET D = A1 * A4 - A3 * A2
20 IF D = 0 THEN 65
30 READ B1, B2
37 LET X1 = (B1*A4 - B2*A2) / D
42 LET X2 = (A1*B2 - A3*B1) / D
55 PRINT X1, X2
60 GOTO 30
65 PRINT "NO UNIQUE SOLUTION"
70 DATA 1, 2, 4
80 DATA 2, -7, 5
85 DATA 1, 3, 4, -7
90 END

12
ext/ply/example/BASIC/maxsin.bas Normal file
View file

@ -0,0 +1,12 @@
5 PRINT "X VALUE", "SINE", "RESOLUTION"
10 READ D
20 LET M = -1
30 FOR X = 0 TO 3 STEP D
40 IF SIN(X) <= M THEN 80
50 LET X0 = X
60 LET M = SIN(X)
80 NEXT X
85 PRINT X0, M, D
90 GOTO 10
100 DATA .1, .01, .001
110 END

13
ext/ply/example/BASIC/powers.bas Normal file
View file

@ -0,0 +1,13 @@
5 PRINT "THIS PROGRAM COMPUTES AND PRINTS THE NTH POWERS"
6 PRINT "OF THE NUMBERS LESS THAN OR EQUAL TO N FOR VARIOUS"
7 PRINT "N FROM 1 THROUGH 7"
8 PRINT
10 FOR N = 1 TO 7
15 PRINT "N = "N
20 FOR I = 1 TO N
30 PRINT I^N,
40 NEXT I
50 PRINT
60 PRINT
70 NEXT N
80 END

4
ext/ply/example/BASIC/rand.bas Normal file
View file

@ -0,0 +1,4 @@
10 FOR I = 1 TO 20
20 PRINT INT(10*RND(0))
30 NEXT I
40 END

20
ext/ply/example/BASIC/sales.bas Normal file
View file

@ -0,0 +1,20 @@
10 FOR I = 1 TO 3
20 READ P(I)
30 NEXT I
40 FOR I = 1 TO 3
50 FOR J = 1 TO 5
60 READ S(I,J)
70 NEXT J
80 NEXT I
90 FOR J = 1 TO 5
100 LET S = 0
110 FOR I = 1 TO 3
120 LET S = S + P(I) * S(I,J)
130 NEXT I
140 PRINT "TOTAL SALES FOR SALESMAN"J, "$"S
150 NEXT J
200 DATA 1.25, 4.30, 2.50
210 DATA 40, 20, 37, 29, 42
220 DATA 10, 16, 3, 21, 8
230 DATA 35, 47, 29, 16, 33
300 END

18
ext/ply/example/BASIC/sears.bas Normal file
View file

@ -0,0 +1,18 @@
1 REM :: THIS PROGRAM COMPUTES HOW MANY TIMES YOU HAVE TO FOLD
2 REM :: A PIECE OF PAPER SO THAT IT IS TALLER THAN THE
3 REM :: SEARS TOWER.
4 REM :: S = HEIGHT OF TOWER (METERS)
5 REM :: T = THICKNESS OF PAPER (MILLIMETERS)
10 LET S = 442
20 LET T = 0.1
30 REM CONVERT T TO METERS
40 LET T = T * .001
50 LET F = 1
60 LET H = T
100 IF H > S THEN 200
120 LET H = 2 * H
125 LET F = F + 1
130 GOTO 100
200 PRINT "NUMBER OF FOLDS ="F
220 PRINT "FINAL HEIGHT ="H
999 END

5
ext/ply/example/BASIC/sqrt1.bas Normal file
View file

@ -0,0 +1,5 @@
10 LET X = 0
20 LET X = X + 1
30 PRINT X, SQR(X)
40 IF X < 100 THEN 20
50 END

4
ext/ply/example/BASIC/sqrt2.bas Normal file
View file

@ -0,0 +1,4 @@
10 FOR X = 1 TO 100
20 PRINT X, SQR(X)
30 NEXT X
40 END

709
ext/ply/example/GardenSnake/GardenSnake.py Normal file
View file

@ -0,0 +1,709 @@
# GardenSnake - a parser generator demonstration program
#
# This implements a modified version of a subset of Python:
# - only 'def', 'return' and 'if' statements
# - 'if' only has 'then' clause (no elif nor else)
# - single-quoted strings only, content in raw format
# - numbers are decimal.Decimal instances (not integers or floats)
# - no print statment; use the built-in 'print' function
# - only < > == + - / * implemented (and unary + -)
# - assignment and tuple assignment work
# - no generators of any sort
# - no ... well, no quite a lot
# Why? I'm thinking about a new indentation-based configuration
# language for a project and wanted to figure out how to do it. Once
# I got that working I needed a way to test it out. My original AST
# was dumb so I decided to target Python's AST and compile it into
# Python code. Plus, it's pretty cool that it only took a day or so
# from sitting down with Ply to having working code.
# This uses David Beazley's Ply from http://www.dabeaz.com/ply/
# This work is hereby released into the Public Domain. To view a copy of
# the public domain dedication, visit
# http://creativecommons.org/licenses/publicdomain/ or send a letter to
# Creative Commons, 543 Howard Street, 5th Floor, San Francisco,
# California, 94105, USA.
#
# Portions of this work are derived from Python's Grammar definition
# and may be covered under the Python copyright and license
#
# Andrew Dalke / Dalke Scientific Software, LLC
# 30 August 2006 / Cape Town, South Africa
# Changelog:
# 30 August - added link to CC license; removed the "swapcase" encoding
# Modifications for inclusion in PLY distribution
import sys
sys.path.insert(0,"../..")
from ply import *
##### Lexer ######
#import lex
import decimal
tokens = (
'DEF',
'IF',
'NAME',
'NUMBER', # Python decimals
'STRING', # single quoted strings only; syntax of raw strings
'LPAR',
'RPAR',
'COLON',
'EQ',
'ASSIGN',
'LT',
'GT',
'PLUS',
'MINUS',
'MULT',
'DIV',
'RETURN',
'WS',
'NEWLINE',
'COMMA',
'SEMICOLON',
'INDENT',
'DEDENT',
'ENDMARKER',
)
#t_NUMBER = r'\d+'
# taken from decmial.py but without the leading sign
def t_NUMBER(t):
r"""(\d+(\.\d*)?|\.\d+)([eE][-+]? \d+)?"""
t.value = decimal.Decimal(t.value)
return t
def t_STRING(t):
r"'([^\\']+|\\'|\\\\)*'" # I think this is right ...
t.value=t.value[1:-1].decode("string-escape") # .swapcase() # for fun
return t
t_COLON = r':'
t_EQ = r'=='
t_ASSIGN = r'='
t_LT = r'<'
t_GT = r'>'
t_PLUS = r'\+'
t_MINUS = r'-'
t_MULT = r'\*'
t_DIV = r'/'
t_COMMA = r','
t_SEMICOLON = r';'
# Ply nicely documented how to do this.
RESERVED = {
"def": "DEF",
"if": "IF",
"return": "RETURN",
}
def t_NAME(t):
r'[a-zA-Z_][a-zA-Z0-9_]*'
t.type = RESERVED.get(t.value, "NAME")
return t
# Putting this before t_WS let it consume lines with only comments in
# them so the latter code never sees the WS part. Not consuming the
# newline. Needed for "if 1: #comment"
def t_comment(t):
r"[ ]*\043[^\n]*" # \043 is '#'
pass
# Whitespace
def t_WS(t):
r' [ ]+ '
if t.lexer.at_line_start and t.lexer.paren_count == 0:
return t
# Don't generate newline tokens when inside of parenthesis, eg
# a = (1,
# 2, 3)
def t_newline(t):
r'\n+'
t.lexer.lineno += len(t.value)
t.type = "NEWLINE"
if t.lexer.paren_count == 0:
return t
def t_LPAR(t):
r'\('
t.lexer.paren_count += 1
return t
def t_RPAR(t):
r'\)'
# check for underflow? should be the job of the parser
t.lexer.paren_count -= 1
return t
def t_error(t):
raise SyntaxError("Unknown symbol %r" % (t.value[0],))
print "Skipping", repr(t.value[0])
t.lexer.skip(1)
## I implemented INDENT / DEDENT generation as a post-processing filter
# The original lex token stream contains WS and NEWLINE characters.
# WS will only occur before any other tokens on a line.
# I have three filters. One tags tokens by adding two attributes.
# "must_indent" is True if the token must be indented from the
# previous code. The other is "at_line_start" which is True for WS
# and the first non-WS/non-NEWLINE on a line. It flags the check so
# see if the new line has changed indication level.
# Python's syntax has three INDENT states
# 0) no colon hence no need to indent
# 1) "if 1: go()" - simple statements have a COLON but no need for an indent
# 2) "if 1:\n go()" - complex statements have a COLON NEWLINE and must indent
NO_INDENT = 0
MAY_INDENT = 1
MUST_INDENT = 2
# only care about whitespace at the start of a line
def track_tokens_filter(lexer, tokens):
lexer.at_line_start = at_line_start = True
indent = NO_INDENT
saw_colon = False
for token in tokens:
token.at_line_start = at_line_start
if token.type == "COLON":
at_line_start = False
indent = MAY_INDENT
token.must_indent = False
elif token.type == "NEWLINE":
at_line_start = True
if indent == MAY_INDENT:
indent = MUST_INDENT
token.must_indent = False
elif token.type == "WS":
assert token.at_line_start == True
at_line_start = True
token.must_indent = False
else:
# A real token; only indent after COLON NEWLINE
if indent == MUST_INDENT:
token.must_indent = True
else:
token.must_indent = False
at_line_start = False
indent = NO_INDENT
yield token
lexer.at_line_start = at_line_start
def _new_token(type, lineno):
tok = lex.LexToken()
tok.type = type
tok.value = None
tok.lineno = lineno
return tok
# Synthesize a DEDENT tag
def DEDENT(lineno):
return _new_token("DEDENT", lineno)
# Synthesize an INDENT tag
def INDENT(lineno):
return _new_token("INDENT", lineno)
# Track the indentation level and emit the right INDENT / DEDENT events.
def indentation_filter(tokens):
# A stack of indentation levels; will never pop item 0
levels = [0]
token = None
depth = 0
prev_was_ws = False
for token in tokens:
## if 1:
## print "Process", token,
## if token.at_line_start:
## print "at_line_start",
## if token.must_indent:
## print "must_indent",
## print
# WS only occurs at the start of the line
# There may be WS followed by NEWLINE so
# only track the depth here. Don't indent/dedent
# until there's something real.
if token.type == "WS":
assert depth == 0
depth = len(token.value)
prev_was_ws = True
# WS tokens are never passed to the parser
continue
if token.type == "NEWLINE":
depth = 0
if prev_was_ws or token.at_line_start:
# ignore blank lines
continue
# pass the other cases on through
yield token
continue
# then it must be a real token (not WS, not NEWLINE)
# which can affect the indentation level
prev_was_ws = False
if token.must_indent:
# The current depth must be larger than the previous level
if not (depth > levels[-1]):
raise IndentationError("expected an indented block")
levels.append(depth)
yield INDENT(token.lineno)
elif token.at_line_start:
# Must be on the same level or one of the previous levels
if depth == levels[-1]:
# At the same level
pass
elif depth > levels[-1]:
raise IndentationError("indentation increase but not in new block")
else:
# Back up; but only if it matches a previous level
try:
i = levels.index(depth)
except ValueError:
raise IndentationError("inconsistent indentation")
for _ in range(i+1, len(levels)):
yield DEDENT(token.lineno)
levels.pop()
yield token
### Finished processing ###
# Must dedent any remaining levels
if len(levels) > 1:
assert token is not None
for _ in range(1, len(levels)):
yield DEDENT(token.lineno)
# The top-level filter adds an ENDMARKER, if requested.
# Python's grammar uses it.
def filter(lexer, add_endmarker = True):
token = None
tokens = iter(lexer.token, None)
tokens = track_tokens_filter(lexer, tokens)
for token in indentation_filter(tokens):
yield token
if add_endmarker:
lineno = 1
if token is not None:
lineno = token.lineno
yield _new_token("ENDMARKER", lineno)
# Combine Ply and my filters into a new lexer
class IndentLexer(object):
def __init__(self, debug=0, optimize=0, lextab='lextab', reflags=0):
self.lexer = lex.lex(debug=debug, optimize=optimize, lextab=lextab, reflags=reflags)
self.token_stream = None
def input(self, s, add_endmarker=True):
self.lexer.paren_count = 0
self.lexer.input(s)
self.token_stream = filter(self.lexer, add_endmarker)
def token(self):
try:
return self.token_stream.next()
except StopIteration:
return None
########## Parser (tokens -> AST) ######
# also part of Ply
#import yacc
# I use the Python AST
from compiler import ast
# Helper function
def Assign(left, right):
names = []
if isinstance(left, ast.Name):
# Single assignment on left
return ast.Assign([ast.AssName(left.name, 'OP_ASSIGN')], right)
elif isinstance(left, ast.Tuple):
# List of things - make sure they are Name nodes
names = []
for child in left.getChildren():
if not isinstance(child, ast.Name):
raise SyntaxError("that assignment not supported")
names.append(child.name)
ass_list = [ast.AssName(name, 'OP_ASSIGN') for name in names]
return ast.Assign([ast.AssTuple(ass_list)], right)
else:
raise SyntaxError("Can't do that yet")
# The grammar comments come from Python's Grammar/Grammar file
## NB: compound_stmt in single_input is followed by extra NEWLINE!
# file_input: (NEWLINE | stmt)* ENDMARKER
def p_file_input_end(p):
"""file_input_end : file_input ENDMARKER"""
p[0] = ast.Stmt(p[1])
def p_file_input(p):
"""file_input : file_input NEWLINE
| file_input stmt
| NEWLINE
| stmt"""
if isinstance(p[len(p)-1], basestring):
if len(p) == 3:
p[0] = p[1]
else:
p[0] = [] # p == 2 --> only a blank line
else:
if len(p) == 3:
p[0] = p[1] + p[2]
else:
p[0] = p[1]
# funcdef: [decorators] 'def' NAME parameters ':' suite
# ignoring decorators
def p_funcdef(p):
"funcdef : DEF NAME parameters COLON suite"
p[0] = ast.Function(None, p[2], tuple(p[3]), (), 0, None, p[5])
# parameters: '(' [varargslist] ')'
def p_parameters(p):
"""parameters : LPAR RPAR
| LPAR varargslist RPAR"""
if len(p) == 3:
p[0] = []
else:
p[0] = p[2]
# varargslist: (fpdef ['=' test] ',')* ('*' NAME [',' '**' NAME] | '**' NAME) |
# highly simplified
def p_varargslist(p):
"""varargslist : varargslist COMMA NAME
| NAME"""
if len(p) == 4:
p[0] = p[1] + p[3]
else:
p[0] = [p[1]]
# stmt: simple_stmt | compound_stmt
def p_stmt_simple(p):
"""stmt : simple_stmt"""
# simple_stmt is a list
p[0] = p[1]
def p_stmt_compound(p):
"""stmt : compound_stmt"""
p[0] = [p[1]]
# simple_stmt: small_stmt (';' small_stmt)* [';'] NEWLINE
def p_simple_stmt(p):
"""simple_stmt : small_stmts NEWLINE
| small_stmts SEMICOLON NEWLINE"""
p[0] = p[1]
def p_small_stmts(p):
"""small_stmts : small_stmts SEMICOLON small_stmt
| small_stmt"""
if len(p) == 4:
p[0] = p[1] + [p[3]]
else:
p[0] = [p[1]]
# small_stmt: expr_stmt | print_stmt | del_stmt | pass_stmt | flow_stmt |
# import_stmt | global_stmt | exec_stmt | assert_stmt
def p_small_stmt(p):
"""small_stmt : flow_stmt
| expr_stmt"""
p[0] = p[1]
# expr_stmt: testlist (augassign (yield_expr|testlist) |
# ('=' (yield_expr|testlist))*)
# augassign: ('+=' | '-=' | '*=' | '/=' | '%=' | '&=' | '|=' | '^=' |
# '<<=' | '>>=' | '**=' | '//=')
def p_expr_stmt(p):
"""expr_stmt : testlist ASSIGN testlist
| testlist """
if len(p) == 2:
# a list of expressions
p[0] = ast.Discard(p[1])
else:
p[0] = Assign(p[1], p[3])
def p_flow_stmt(p):
"flow_stmt : return_stmt"
p[0] = p[1]
# return_stmt: 'return' [testlist]
def p_return_stmt(p):
"return_stmt : RETURN testlist"
p[0] = ast.Return(p[2])
def p_compound_stmt(p):
"""compound_stmt : if_stmt
| funcdef"""
p[0] = p[1]
def p_if_stmt(p):
'if_stmt : IF test COLON suite'
p[0] = ast.If([(p[2], p[4])], None)
def p_suite(p):
"""suite : simple_stmt
| NEWLINE INDENT stmts DEDENT"""
if len(p) == 2:
p[0] = ast.Stmt(p[1])
else:
p[0] = ast.Stmt(p[3])
def p_stmts(p):
"""stmts : stmts stmt
| stmt"""
if len(p) == 3:
p[0] = p[1] + p[2]
else:
p[0] = p[1]
## No using Python's approach because Ply supports precedence
# comparison: expr (comp_op expr)*
# arith_expr: term (('+'|'-') term)*
# term: factor (('*'|'/'|'%'|'//') factor)*
# factor: ('+'|'-'|'~') factor | power
# comp_op: '<'|'>'|'=='|'>='|'<='|'<>'|'!='|'in'|'not' 'in'|'is'|'is' 'not'
def make_lt_compare((left, right)):
return ast.Compare(left, [('<', right),])
def make_gt_compare((left, right)):
return ast.Compare(left, [('>', right),])
def make_eq_compare((left, right)):
return ast.Compare(left, [('==', right),])
binary_ops = {
"+": ast.Add,
"-": ast.Sub,
"*": ast.Mul,
"/": ast.Div,
"<": make_lt_compare,
">": make_gt_compare,
"==": make_eq_compare,
}
unary_ops = {
"+": ast.UnaryAdd,
"-": ast.UnarySub,
}
precedence = (
("left", "EQ", "GT", "LT"),
("left", "PLUS", "MINUS"),
("left", "MULT", "DIV"),
)
def p_comparison(p):
"""comparison : comparison PLUS comparison
| comparison MINUS comparison
| comparison MULT comparison
| comparison DIV comparison
| comparison LT comparison
| comparison EQ comparison
| comparison GT comparison
| PLUS comparison
| MINUS comparison
| power"""
if len(p) == 4:
p[0] = binary_ops[p[2]]((p[1], p[3]))
elif len(p) == 3:
p[0] = unary_ops[p[1]](p[2])
else:
p[0] = p[1]
# power: atom trailer* ['**' factor]
# trailers enables function calls. I only allow one level of calls
# so this is 'trailer'
def p_power(p):
"""power : atom
| atom trailer"""
if len(p) == 2:
p[0] = p[1]
else:
if p[2][0] == "CALL":
p[0] = ast.CallFunc(p[1], p[2][1], None, None)
else:
raise AssertionError("not implemented")
def p_atom_name(p):
"""atom : NAME"""
p[0] = ast.Name(p[1])
def p_atom_number(p):
"""atom : NUMBER
| STRING"""
p[0] = ast.Const(p[1])
def p_atom_tuple(p):
"""atom : LPAR testlist RPAR"""
p[0] = p[2]
# trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME
def p_trailer(p):
"trailer : LPAR arglist RPAR"
p[0] = ("CALL", p[2])
# testlist: test (',' test)* [',']
# Contains shift/reduce error
def p_testlist(p):
"""testlist : testlist_multi COMMA
| testlist_multi """
if len(p) == 2:
p[0] = p[1]
else:
# May need to promote singleton to tuple
if isinstance(p[1], list):
p[0] = p[1]
else:
p[0] = [p[1]]
# Convert into a tuple?
if isinstance(p[0], list):
p[0] = ast.Tuple(p[0])
def p_testlist_multi(p):
"""testlist_multi : testlist_multi COMMA test
| test"""
if len(p) == 2:
# singleton
p[0] = p[1]
else:
if isinstance(p[1], list):
p[0] = p[1] + [p[3]]
else:
# singleton -> tuple
p[0] = [p[1], p[3]]
# test: or_test ['if' or_test 'else' test] | lambdef
# as I don't support 'and', 'or', and 'not' this works down to 'comparison'
def p_test(p):
"test : comparison"
p[0] = p[1]
# arglist: (argument ',')* (argument [',']| '*' test [',' '**' test] | '**' test)
# XXX INCOMPLETE: this doesn't allow the trailing comma
def p_arglist(p):
"""arglist : arglist COMMA argument
| argument"""
if len(p) == 4:
p[0] = p[1] + [p[3]]
else:
p[0] = [p[1]]
# argument: test [gen_for] | test '=' test # Really [keyword '='] test
def p_argument(p):
"argument : test"
p[0] = p[1]
def p_error(p):
#print "Error!", repr(p)
raise SyntaxError(p)
class GardenSnakeParser(object):
def __init__(self, lexer = None):
if lexer is None:
lexer = IndentLexer()
self.lexer = lexer
self.parser = yacc.yacc(start="file_input_end")
def parse(self, code):
self.lexer.input(code)
result = self.parser.parse(lexer = self.lexer)
return ast.Module(None, result)
###### Code generation ######
from compiler import misc, syntax, pycodegen
class GardenSnakeCompiler(object):
def __init__(self):
self.parser = GardenSnakeParser()
def compile(self, code, filename="<string>"):
tree = self.parser.parse(code)
#print tree
misc.set_filename(filename, tree)
syntax.check(tree)
gen = pycodegen.ModuleCodeGenerator(tree)
code = gen.getCode()
return code
####### Test code #######
compile = GardenSnakeCompiler().compile
code = r"""
print('LET\'S TRY THIS \\OUT')
#Comment here
def x(a):
print('called with',a)
if a == 1:
return 2
if a*2 > 10: return 999 / 4
# Another comment here
return a+2*3
ints = (1, 2,
3, 4,
5)
print('mutiline-expression', ints)
t = 4+1/3*2+6*(9-5+1)
print('predence test; should be 34+2/3:', t, t==(34+2/3))
print('numbers', 1,2,3,4,5)
if 1:
8
a=9
print(x(a))
print(x(1))
print(x(2))
print(x(8),'3')
print('this is decimal', 1/5)
print('BIG DECIMAL', 1.234567891234567e12345)
"""
# Set up the GardenSnake run-time environment
def print_(*args):
print "-->", " ".join(map(str,args))
globals()["print"] = print_
compiled_code = compile(code)
exec compiled_code in globals()
print "Done"

5
ext/ply/example/GardenSnake/README Normal file
View file

@ -0,0 +1,5 @@
This example is Andrew Dalke's GardenSnake language. It shows how to process an
indentation-like language like Python. Further details can be found here:
http://dalkescientific.com/writings/diary/archive/2006/08/30/gardensnake_language.html

10
ext/ply/example/README Normal file
View file

@ -0,0 +1,10 @@
Simple examples:
calc - Simple calculator
classcalc - Simple calculate defined as a class
Complex examples
ansic - ANSI C grammar from K&R
BASIC - A small BASIC interpreter
GardenSnake - A simple python-like language
yply - Converts Unix yacc files to PLY programs.

11
ext/ply/example/ansic/clex.py
View file

@ -4,7 +4,10 @@
# A lexer for ANSI C.
# ----------------------------------------------------------------------
import lex
import sys
sys.path.insert(0,"../..")
import ply.lex as lex
# Reserved words
reserved = (
@ -53,7 +56,7 @@ t_ignore = ' \t\x0c'
# Newlines
def t_NEWLINE(t):
r'\n+'
t.lineno += t.value.count("\n")
t.lexer.lineno += t.value.count("\n")
# Operators
t_PLUS = r'\+'
@ -64,7 +67,7 @@ t_MOD = r'%'
t_OR = r'\|'
t_AND = r'&'
t_NOT = r'~'
t_XOR = r'^'
t_XOR = r'\^'
t_LSHIFT = r'<<'
t_RSHIFT = r'>>'
t_LOR = r'\|\|'
@ -149,7 +152,7 @@ def t_preprocessor(t):
def t_error(t):
print "Illegal character %s" % repr(t.value[0])
t.skip(1)
t.lexer.skip(1)
lexer = lex.lex(optimize=1)
if __name__ == "__main__":

8
ext/ply/example/ansic/cparse.py
View file

@ -4,8 +4,9 @@
# Simple parser for ANSI C. Based on the grammar in K&R, 2nd Ed.
# -----------------------------------------------------------------------------
import yacc
import sys
import clex
import ply.yacc as yacc
# Get the token map
tokens = clex.tokens
@ -852,7 +853,10 @@ def p_error(t):
import profile
# Build the grammar
profile.run("yacc.yacc()")
yacc.yacc(method='LALR')
#profile.run("yacc.yacc(method='LALR')")

87
ext/ply/example/calc/calc.py
View file

@ -5,21 +5,17 @@
# "Lex and Yacc", p. 63.
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"../..")
tokens = (
'NAME','NUMBER',
'PLUS','MINUS','TIMES','DIVIDE','EQUALS',
'LPAREN','RPAREN',
)
literals = ['=','+','-','*','/', '(',')']
# Tokens
t_PLUS = r'\+'
t_MINUS = r'-'
t_TIMES = r'\*'
t_DIVIDE = r'/'
t_EQUALS = r'='
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_NAME = r'[a-zA-Z_][a-zA-Z0-9_]*'
def t_NUMBER(t):
@ -35,69 +31,69 @@ t_ignore = " \t"
def t_newline(t):
r'\n+'
t.lineno += t.value.count("\n")
t.lexer.lineno += t.value.count("\n")
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.skip(1)
t.lexer.skip(1)
# Build the lexer
import lex
import ply.lex as lex
lex.lex()
# Parsing rules
precedence = (
('left','PLUS','MINUS'),
('left','TIMES','DIVIDE'),
('left','+','-'),
('left','*','/'),
('right','UMINUS'),
)
# dictionary of names
names = { }
def p_statement_assign(t):
'statement : NAME EQUALS expression'
names[t[1]] = t[3]
def p_statement_assign(p):
'statement : NAME "=" expression'
names[p[1]] = p[3]
def p_statement_expr(t):
def p_statement_expr(p):
'statement : expression'
print t[1]
print p[1]
def p_expression_binop(t):
'''expression : expression PLUS expression
| expression MINUS expression
| expression TIMES expression
| expression DIVIDE expression'''
if t[2] == '+' : t[0] = t[1] + t[3]
elif t[2] == '-': t[0] = t[1] - t[3]
elif t[2] == '*': t[0] = t[1] * t[3]
elif t[2] == '/': t[0] = t[1] / t[3]
def p_expression_binop(p):
'''expression : expression '+' expression
| expression '-' expression
| expression '*' expression
| expression '/' expression'''
if p[2] == '+' : p[0] = p[1] + p[3]
elif p[2] == '-': p[0] = p[1] - p[3]
elif p[2] == '*': p[0] = p[1] * p[3]
elif p[2] == '/': p[0] = p[1] / p[3]
def p_expression_uminus(t):
'expression : MINUS expression %prec UMINUS'
t[0] = -t[2]
def p_expression_uminus(p):
"expression : '-' expression %prec UMINUS"
p[0] = -p[2]
def p_expression_group(t):
'expression : LPAREN expression RPAREN'
t[0] = t[2]
def p_expression_group(p):
"expression : '(' expression ')'"
p[0] = p[2]
def p_expression_number(t):
'expression : NUMBER'
t[0] = t[1]
def p_expression_number(p):
"expression : NUMBER"
p[0] = p[1]
def p_expression_name(t):
'expression : NAME'
def p_expression_name(p):
"expression : NAME"
try:
t[0] = names[t[1]]
p[0] = names[p[1]]
except LookupError:
print "Undefined name '%s'" % t[1]
t[0] = 0
print "Undefined name '%s'" % p[1]
p[0] = 0
def p_error(t):
print "Syntax error at '%s'" % t.value
def p_error(p):
print "Syntax error at '%s'" % p.value
import yacc
import ply.yacc as yacc
yacc.yacc()
while 1:
@ -105,4 +101,5 @@ while 1:
s = raw_input('calc > ')
except EOFError:
break
if not s: continue
yacc.parse(s)

152
ext/ply/example/classcalc/calc.py Normal file
View file

@ -0,0 +1,152 @@
#!/usr/bin/env python
# -----------------------------------------------------------------------------
# calc.py
#
# A simple calculator with variables. This is from O'Reilly's
# "Lex and Yacc", p. 63.
#
# Class-based example contributed to PLY by David McNab
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"../..")
import readline
import ply.lex as lex
import ply.yacc as yacc
import os
class Parser:
"""
Base class for a lexer/parser that has the rules defined as methods
"""
tokens = ()
precedence = ()
def __init__(self, **kw):
self.debug = kw.get('debug', 0)
self.names = { }
try:
modname = os.path.split(os.path.splitext(__file__)[0])[1] + "_" + self.__class__.__name__
except:
modname = "parser"+"_"+self.__class__.__name__
self.debugfile = modname + ".dbg"
self.tabmodule = modname + "_" + "parsetab"
#print self.debugfile, self.tabmodule
# Build the lexer and parser
lex.lex(module=self, debug=self.debug)
yacc.yacc(module=self,
debug=self.debug,
debugfile=self.debugfile,
tabmodule=self.tabmodule)
def run(self):
while 1:
try:
s = raw_input('calc > ')
except EOFError:
break
if not s: continue
yacc.parse(s)
class Calc(Parser):
tokens = (
'NAME','NUMBER',
'PLUS','MINUS','EXP', 'TIMES','DIVIDE','EQUALS',
'LPAREN','RPAREN',
)
# Tokens
t_PLUS = r'\+'
t_MINUS = r'-'
t_EXP = r'\*\*'
t_TIMES = r'\*'
t_DIVIDE = r'/'
t_EQUALS = r'='
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_NAME = r'[a-zA-Z_][a-zA-Z0-9_]*'
def t_NUMBER(self, t):
r'\d+'
try:
t.value = int(t.value)
except ValueError:
print "Integer value too large", t.value
t.value = 0
#print "parsed number %s" % repr(t.value)
return t
t_ignore = " \t"
def t_newline(self, t):
r'\n+'
t.lexer.lineno += t.value.count("\n")
def t_error(self, t):
print "Illegal character '%s'" % t.value[0]
t.lexer.skip(1)
# Parsing rules
precedence = (
('left','PLUS','MINUS'),
('left','TIMES','DIVIDE'),
('left', 'EXP'),
('right','UMINUS'),
)
def p_statement_assign(self, p):
'statement : NAME EQUALS expression'
self.names[p[1]] = p[3]
def p_statement_expr(self, p):
'statement : expression'
print p[1]
def p_expression_binop(self, p):
"""
expression : expression PLUS expression
| expression MINUS expression
| expression TIMES expression
| expression DIVIDE expression
| expression EXP expression
"""
#print [repr(p[i]) for i in range(0,4)]
if p[2] == '+' : p[0] = p[1] + p[3]
elif p[2] == '-': p[0] = p[1] - p[3]
elif p[2] == '*': p[0] = p[1] * p[3]
elif p[2] == '/': p[0] = p[1] / p[3]
elif p[2] == '**': p[0] = p[1] ** p[3]
def p_expression_uminus(self, p):
'expression : MINUS expression %prec UMINUS'
p[0] = -p[2]
def p_expression_group(self, p):
'expression : LPAREN expression RPAREN'
p[0] = p[2]
def p_expression_number(self, p):
'expression : NUMBER'
p[0] = p[1]
def p_expression_name(self, p):
'expression : NAME'
try:
p[0] = self.names[p[1]]
except LookupError:
print "Undefined name '%s'" % p[1]
p[0] = 0
def p_error(self, p):
print "Syntax error at '%s'" % p.value
if __name__ == '__main__':
calc = Calc()
calc.run()

2
ext/ply/example/cleanup.sh Normal file
View file

@ -0,0 +1,2 @@
#!/bin/sh
rm -f */*.pyc */parsetab.py */parser.out */*~ */*.class

8
ext/ply/example/hedit/hedit.py
View file

@ -14,6 +14,10 @@
# such tokens
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"../..")
tokens = (
'H_EDIT_DESCRIPTOR',
)
@ -34,10 +38,10 @@ def t_H_EDIT_DESCRIPTOR(t):
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.skip(1)
t.lexer.skip(1)
# Build the lexer
import lex
import ply.lex as lex
lex.lex()
lex.runmain()

155
ext/ply/example/newclasscalc/calc.py Normal file
View file

@ -0,0 +1,155 @@
#!/usr/bin/env python
# -----------------------------------------------------------------------------
# calc.py
#
# A simple calculator with variables. This is from O'Reilly's
# "Lex and Yacc", p. 63.
#
# Class-based example contributed to PLY by David McNab.
#
# Modified to use new-style classes. Test case.
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"../..")
import readline
import ply.lex as lex
import ply.yacc as yacc
import os
class Parser(object):
"""
Base class for a lexer/parser that has the rules defined as methods
"""
tokens = ()
precedence = ()
def __init__(self, **kw):
self.debug = kw.get('debug', 0)
self.names = { }
try:
modname = os.path.split(os.path.splitext(__file__)[0])[1] + "_" + self.__class__.__name__
except:
modname = "parser"+"_"+self.__class__.__name__
self.debugfile = modname + ".dbg"
self.tabmodule = modname + "_" + "parsetab"
#print self.debugfile, self.tabmodule
# Build the lexer and parser
lex.lex(module=self, debug=self.debug)
yacc.yacc(module=self,
debug=self.debug,
debugfile=self.debugfile,
tabmodule=self.tabmodule)
def run(self):
while 1:
try:
s = raw_input('calc > ')
except EOFError:
break
if not s: continue
yacc.parse(s)
class Calc(Parser):
tokens = (
'NAME','NUMBER',
'PLUS','MINUS','EXP', 'TIMES','DIVIDE','EQUALS',
'LPAREN','RPAREN',
)
# Tokens
t_PLUS = r'\+'
t_MINUS = r'-'
t_EXP = r'\*\*'
t_TIMES = r'\*'
t_DIVIDE = r'/'
t_EQUALS = r'='
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_NAME = r'[a-zA-Z_][a-zA-Z0-9_]*'
def t_NUMBER(self, t):
r'\d+'
try:
t.value = int(t.value)
except ValueError:
print "Integer value too large", t.value
t.value = 0
#print "parsed number %s" % repr(t.value)
return t
t_ignore = " \t"
def t_newline(self, t):
r'\n+'
t.lexer.lineno += t.value.count("\n")
def t_error(self, t):
print "Illegal character '%s'" % t.value[0]
t.lexer.skip(1)
# Parsing rules
precedence = (
('left','PLUS','MINUS'),
('left','TIMES','DIVIDE'),
('left', 'EXP'),
('right','UMINUS'),
)
def p_statement_assign(self, p):
'statement : NAME EQUALS expression'
self.names[p[1]] = p[3]
def p_statement_expr(self, p):
'statement : expression'
print p[1]
def p_expression_binop(self, p):
"""
expression : expression PLUS expression
| expression MINUS expression
| expression TIMES expression
| expression DIVIDE expression
| expression EXP expression
"""
#print [repr(p[i]) for i in range(0,4)]
if p[2] == '+' : p[0] = p[1] + p[3]
elif p[2] == '-': p[0] = p[1] - p[3]
elif p[2] == '*': p[0] = p[1] * p[3]
elif p[2] == '/': p[0] = p[1] / p[3]
elif p[2] == '**': p[0] = p[1] ** p[3]
def p_expression_uminus(self, p):
'expression : MINUS expression %prec UMINUS'
p[0] = -p[2]
def p_expression_group(self, p):
'expression : LPAREN expression RPAREN'
p[0] = p[2]
def p_expression_number(self, p):
'expression : NUMBER'
p[0] = p[1]
def p_expression_name(self, p):
'expression : NAME'
try:
p[0] = self.names[p[1]]
except LookupError:
print "Undefined name '%s'" % p[1]
p[0] = 0
def p_error(self, p):
print "Syntax error at '%s'" % p.value
if __name__ == '__main__':
calc = Calc()
calc.run()

11
ext/ply/example/optcalc/calc.py
View file

@ -5,6 +5,9 @@
# "Lex and Yacc", p. 63.
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"../..")
tokens = (
'NAME','NUMBER',
'PLUS','MINUS','TIMES','DIVIDE','EQUALS',
@ -35,14 +38,14 @@ t_ignore = " \t"
def t_newline(t):
r'\n+'
t.lineno += t.value.count("\n")
t.lexer.lineno += t.value.count("\n")
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.skip(1)
t.lexer.skip(1)
# Build the lexer
import lex
import ply.lex as lex
lex.lex(optimize=1)
# Parsing rules
@ -98,7 +101,7 @@ def p_expression_name(t):
def p_error(t):
print "Syntax error at '%s'" % t.value
import yacc
import ply.yacc as yacc
yacc.yacc(optimize=1)
while 1:

114
ext/ply/example/unicalc/calc.py Normal file
View file

@ -0,0 +1,114 @@
# -----------------------------------------------------------------------------
# calc.py
#
# A simple calculator with variables. This is from O'Reilly's
# "Lex and Yacc", p. 63.
#
# This example uses unicode strings for tokens, docstrings, and input.
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"../..")
tokens = (
'NAME','NUMBER',
'PLUS','MINUS','TIMES','DIVIDE','EQUALS',
'LPAREN','RPAREN',
)
# Tokens
t_PLUS = ur'\+'
t_MINUS = ur'-'
t_TIMES = ur'\*'
t_DIVIDE = ur'/'
t_EQUALS = ur'='
t_LPAREN = ur'\('
t_RPAREN = ur'\)'
t_NAME = ur'[a-zA-Z_][a-zA-Z0-9_]*'
def t_NUMBER(t):
ur'\d+'
try:
t.value = int(t.value)
except ValueError:
print "Integer value too large", t.value
t.value = 0
return t
t_ignore = u" \t"
def t_newline(t):
ur'\n+'
t.lexer.lineno += t.value.count("\n")
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.lexer.skip(1)
# Build the lexer
import ply.lex as lex
lex.lex()
# Parsing rules
precedence = (
('left','PLUS','MINUS'),
('left','TIMES','DIVIDE'),
('right','UMINUS'),
)
# dictionary of names
names = { }
def p_statement_assign(p):
'statement : NAME EQUALS expression'
names[p[1]] = p[3]
def p_statement_expr(p):
'statement : expression'
print p[1]
def p_expression_binop(p):
'''expression : expression PLUS expression
| expression MINUS expression
| expression TIMES expression
| expression DIVIDE expression'''
if p[2] == u'+' : p[0] = p[1] + p[3]
elif p[2] == u'-': p[0] = p[1] - p[3]
elif p[2] == u'*': p[0] = p[1] * p[3]
elif p[2] == u'/': p[0] = p[1] / p[3]
def p_expression_uminus(p):
'expression : MINUS expression %prec UMINUS'
p[0] = -p[2]
def p_expression_group(p):
'expression : LPAREN expression RPAREN'
p[0] = p[2]
def p_expression_number(p):
'expression : NUMBER'
p[0] = p[1]
def p_expression_name(p):
'expression : NAME'
try:
p[0] = names[p[1]]
except LookupError:
print "Undefined name '%s'" % p[1]
p[0] = 0
def p_error(p):
print "Syntax error at '%s'" % p.value
import ply.yacc as yacc
yacc.yacc()
while 1:
try:
s = raw_input('calc > ')
except EOFError:
break
if not s: continue
yacc.parse(unicode(s))

41
ext/ply/example/yply/README Normal file
View file

@ -0,0 +1,41 @@
yply.py
This example implements a program yply.py that converts a UNIX-yacc
specification file into a PLY-compatible program. To use, simply
run it like this:
% python yply.py [-nocode] inputfile.y >myparser.py
The output of this program is Python code. In the output,
any C code in the original file is included, but is commented out.
If you use the -nocode option, then all of the C code in the
original file is just discarded.
To use the resulting grammer with PLY, you'll need to edit the
myparser.py file. Within this file, some stub code is included that
can be used to test the construction of the parsing tables. However,
you'll need to do more editing to make a workable parser.
Disclaimer: This just an example I threw together in an afternoon.
It might have some bugs. However, it worked when I tried it on
a yacc-specified C++ parser containing 442 rules and 855 parsing
states.
Comments:
1. This example does not parse specification files meant for lex/flex.
You'll need to specify the tokenizer on your own.
2. This example shows a number of interesting PLY features including
- Parsing of literal text delimited by nested parentheses
- Some interaction between the parser and the lexer.
- Use of literals in the grammar specification
- One pass compilation. The program just emits the result,
there is no intermediate parse tree.
3. This program could probably be cleaned up and enhanced a lot.
It would be great if someone wanted to work on this (hint).
-Dave

112
ext/ply/example/yply/ylex.py Normal file
View file

@ -0,0 +1,112 @@
# lexer for yacc-grammars
#
# Author: David Beazley (dave@dabeaz.com)
# Date : October 2, 2006
import sys
sys.path.append("../..")
from ply import *
tokens = (
'LITERAL','SECTION','TOKEN','LEFT','RIGHT','PREC','START','TYPE','NONASSOC','UNION','CODE',
'ID','QLITERAL','NUMBER',
)
states = (('code','exclusive'),)
literals = [ ';', ',', '<', '>', '|',':' ]
t_ignore = ' \t'
t_TOKEN = r'%token'
t_LEFT = r'%left'
t_RIGHT = r'%right'
t_NONASSOC = r'%nonassoc'
t_PREC = r'%prec'
t_START = r'%start'
t_TYPE = r'%type'
t_UNION = r'%union'
t_ID = r'[a-zA-Z_][a-zA-Z_0-9]*'
t_QLITERAL = r'''(?P<quote>['"]).*?(?P=quote)'''
t_NUMBER = r'\d+'
def t_SECTION(t):
r'%%'
if getattr(t.lexer,"lastsection",0):
t.value = t.lexer.lexdata[t.lexpos+2:]
t.lexer.lexpos = len(t.lexer.lexdata)
else:
t.lexer.lastsection = 0
return t
# Comments
def t_ccomment(t):
r'/\*(.|\n)*?\*/'
t.lineno += t.value.count('\n')
t_ignore_cppcomment = r'//.*'
def t_LITERAL(t):
r'%\{(.|\n)*?%\}'
t.lexer.lineno += t.value.count("\n")
return t
def t_NEWLINE(t):
r'\n'
t.lexer.lineno += 1
def t_code(t):
r'\{'
t.lexer.codestart = t.lexpos
t.lexer.level = 1
t.lexer.begin('code')
def t_code_ignore_string(t):
r'\"([^\\\n]|(\\.))*?\"'
def t_code_ignore_char(t):
r'\'([^\\\n]|(\\.))*?\''
def t_code_ignore_comment(t):
r'/\*(.|\n)*?\*/'
def t_code_ignore_cppcom(t):
r'//.*'
def t_code_lbrace(t):
r'\{'
t.lexer.level += 1
def t_code_rbrace(t):
r'\}'
t.lexer.level -= 1
if t.lexer.level == 0:
t.type = 'CODE'
t.value = t.lexer.lexdata[t.lexer.codestart:t.lexpos+1]
t.lexer.begin('INITIAL')
t.lexer.lineno += t.value.count('\n')
return t
t_code_ignore_nonspace = r'[^\s\}\'\"\{]+'
t_code_ignore_whitespace = r'\s+'
t_code_ignore = ""
def t_code_error(t):
raise RuntimeError
def t_error(t):
print "%d: Illegal character '%s'" % (t.lineno, t.value[0])
print t.value
t.lexer.skip(1)
lex.lex()
if __name__ == '__main__':
lex.runmain()

217
ext/ply/example/yply/yparse.py Normal file
View file

@ -0,0 +1,217 @@
# parser for Unix yacc-based grammars
#
# Author: David Beazley (dave@dabeaz.com)
# Date : October 2, 2006
import ylex
tokens = ylex.tokens
from ply import *
tokenlist = []
preclist = []
emit_code = 1
def p_yacc(p):
'''yacc : defsection rulesection'''
def p_defsection(p):
'''defsection : definitions SECTION
| SECTION'''
p.lexer.lastsection = 1
print "tokens = ", repr(tokenlist)
print
print "precedence = ", repr(preclist)
print
print "# -------------- RULES ----------------"
print
def p_rulesection(p):
'''rulesection : rules SECTION'''
print "# -------------- RULES END ----------------"
print_code(p[2],0)
def p_definitions(p):
'''definitions : definitions definition
| definition'''
def p_definition_literal(p):
'''definition : LITERAL'''
print_code(p[1],0)
def p_definition_start(p):
'''definition : START ID'''
print "start = '%s'" % p[2]
def p_definition_token(p):
'''definition : toktype opttype idlist optsemi '''
for i in p[3]:
if i[0] not in "'\"":
tokenlist.append(i)
if p[1] == '%left':
preclist.append(('left',) + tuple(p[3]))
elif p[1] == '%right':
preclist.append(('right',) + tuple(p[3]))
elif p[1] == '%nonassoc':
preclist.append(('nonassoc',)+ tuple(p[3]))
def p_toktype(p):
'''toktype : TOKEN
| LEFT
| RIGHT
| NONASSOC'''
p[0] = p[1]
def p_opttype(p):
'''opttype : '<' ID '>'
| empty'''
def p_idlist(p):
'''idlist : idlist optcomma tokenid
| tokenid'''
if len(p) == 2:
p[0] = [p[1]]
else:
p[0] = p[1]
p[1].append(p[3])
def p_tokenid(p):
'''tokenid : ID
| ID NUMBER
| QLITERAL
| QLITERAL NUMBER'''
p[0] = p[1]
def p_optsemi(p):
'''optsemi : ';'
| empty'''
def p_optcomma(p):
'''optcomma : ','
| empty'''
def p_definition_type(p):
'''definition : TYPE '<' ID '>' namelist optsemi'''
# type declarations are ignored
def p_namelist(p):
'''namelist : namelist optcomma ID
| ID'''
def p_definition_union(p):
'''definition : UNION CODE optsemi'''
# Union declarations are ignored
def p_rules(p):
'''rules : rules rule
| rule'''
if len(p) == 2:
rule = p[1]
else:
rule = p[2]
# Print out a Python equivalent of this rule
embedded = [ ] # Embedded actions (a mess)
embed_count = 0
rulename = rule[0]
rulecount = 1
for r in rule[1]:
# r contains one of the rule possibilities
print "def p_%s_%d(p):" % (rulename,rulecount)
prod = []
prodcode = ""
for i in range(len(r)):
item = r[i]
if item[0] == '{': # A code block
if i == len(r) - 1:
prodcode = item
break
else:
# an embedded action
embed_name = "_embed%d_%s" % (embed_count,rulename)
prod.append(embed_name)
embedded.append((embed_name,item))
embed_count += 1
else:
prod.append(item)
print " '''%s : %s'''" % (rulename, " ".join(prod))
# Emit code
print_code(prodcode,4)
print
rulecount += 1
for e,code in embedded:
print "def p_%s(p):" % e
print " '''%s : '''" % e
print_code(code,4)
print
def p_rule(p):
'''rule : ID ':' rulelist ';' '''
p[0] = (p[1],[p[3]])
def p_rule2(p):
'''rule : ID ':' rulelist morerules ';' '''
p[4].insert(0,p[3])
p[0] = (p[1],p[4])
def p_rule_empty(p):
'''rule : ID ':' ';' '''
p[0] = (p[1],[[]])
def p_rule_empty2(p):
'''rule : ID ':' morerules ';' '''
p[3].insert(0,[])
p[0] = (p[1],p[3])
def p_morerules(p):
'''morerules : morerules '|' rulelist
| '|' rulelist
| '|' '''
if len(p) == 2:
p[0] = [[]]
elif len(p) == 3:
p[0] = [p[2]]
else:
p[0] = p[1]
p[0].append(p[3])
# print "morerules", len(p), p[0]
def p_rulelist(p):
'''rulelist : rulelist ruleitem
| ruleitem'''
if len(p) == 2:
p[0] = [p[1]]
else:
p[0] = p[1]
p[1].append(p[2])
def p_ruleitem(p):
'''ruleitem : ID
| QLITERAL
| CODE
| PREC'''
p[0] = p[1]
def p_empty(p):
'''empty : '''
def p_error(p):
pass
yacc.yacc(debug=0)
def print_code(code,indent):
if not emit_code: return
codelines = code.splitlines()
for c in codelines:
print "%s# %s" % (" "*indent,c)

53
ext/ply/example/yply/yply.py Normal file
View file

@ -0,0 +1,53 @@
#!/usr/local/bin/python
# yply.py
#
# Author: David Beazley (dave@dabeaz.com)
# Date : October 2, 2006
#
# Converts a UNIX-yacc specification file into a PLY-compatible
# specification. To use, simply do this:
#
# % python yply.py [-nocode] inputfile.y >myparser.py
#
# The output of this program is Python code. In the output,
# any C code in the original file is included, but is commented.
# If you use the -nocode option, then all of the C code in the
# original file is discarded.
#
# Disclaimer: This just an example I threw together in an afternoon.
# It might have some bugs. However, it worked when I tried it on
# a yacc-specified C++ parser containing 442 rules and 855 parsing
# states.
#
import sys
sys.path.insert(0,"../..")
import ylex
import yparse
from ply import *
if len(sys.argv) == 1:
print "usage : yply.py [-nocode] inputfile"
raise SystemExit
if len(sys.argv) == 3:
if sys.argv[1] == '-nocode':
yparse.emit_code = 0
else:
print "Unknown option '%s'" % sys.argv[1]
raise SystemExit
filename = sys.argv[2]
else:
filename = sys.argv[1]
yacc.parse(open(filename).read())
print """
if __name__ == '__main__':
from ply import *
yacc.yacc()
"""

681
ext/ply/lex.py
View file

@ -1,681 +0,0 @@
#-----------------------------------------------------------------------------
# ply: lex.py
#
# Author: David M. Beazley (beazley@cs.uchicago.edu)
# Department of Computer Science
# University of Chicago
# Chicago, IL 60637
#
# Copyright (C) 2001, David M. Beazley
#
# $Header: /home/stever/bk/newmem2/ext/ply/lex.py 1.1 03/06/06 14:53:34-00:00 stever@ $
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
# See the file COPYING for a complete copy of the LGPL.
#
#
# This module automatically constructs a lexical analysis module from regular
# expression rules defined in a user-defined module. The idea is essentially the same
# as that used in John Aycock's Spark framework, but the implementation works
# at the module level rather than requiring the use of classes.
#
# This module tries to provide an interface that is closely modeled after
# the traditional lex interface in Unix. It also differs from Spark
# in that:
#
# - It provides more extensive error checking and reporting if
# the user supplies a set of regular expressions that can't
# be compiled or if there is any other kind of a problem in
# the specification.
#
# - The interface is geared towards LALR(1) and LR(1) parser
# generators. That is tokens are generated one at a time
# rather than being generated in advanced all in one step.
#
# There are a few limitations of this module
#
# - The module interface makes it somewhat awkward to support more
# than one lexer at a time. Although somewhat inelegant from a
# design perspective, this is rarely a practical concern for
# most compiler projects.
#
# - The lexer requires that the entire input text be read into
# a string before scanning. I suppose that most machines have
# enough memory to make this a minor issues, but it makes
# the lexer somewhat difficult to use in interactive sessions
# or with streaming data.
#
#-----------------------------------------------------------------------------
r"""
lex.py
This module builds lex-like scanners based on regular expression rules.
To use the module, simply write a collection of regular expression rules
and actions like this:
# lexer.py
import lex
# Define a list of valid tokens
tokens = (
'IDENTIFIER', 'NUMBER', 'PLUS', 'MINUS'
)
# Define tokens as functions
def t_IDENTIFIER(t):
r' ([a-zA-Z_](\w|_)* '
return t
def t_NUMBER(t):
r' \d+ '
return t
# Some simple tokens with no actions
t_PLUS = r'\+'
t_MINUS = r'-'
# Initialize the lexer
lex.lex()
The tokens list is required and contains a complete list of all valid
token types that the lexer is allowed to produce. Token types are
restricted to be valid identifiers. This means that 'MINUS' is a valid
token type whereas '-' is not.
Rules are defined by writing a function with a name of the form
t_rulename. Each rule must accept a single argument which is
a token object generated by the lexer. This token has the following
attributes:
t.type = type string of the token. This is initially set to the
name of the rule without the leading t_
t.value = The value of the lexeme.
t.lineno = The value of the line number where the token was encountered
For example, the t_NUMBER() rule above might be called with the following:
t.type = 'NUMBER'
t.value = '42'
t.lineno = 3
Each rule returns the token object it would like to supply to the
parser. In most cases, the token t is returned with few, if any
modifications. To discard a token for things like whitespace or
comments, simply return nothing. For instance:
def t_whitespace(t):
r' \s+ '
pass
For faster lexing, you can also define this in terms of the ignore set like this:
t_ignore = ' \t'
The characters in this string are ignored by the lexer. Use of this feature can speed
up parsing significantly since scanning will immediately proceed to the next token.
lex requires that the token returned by each rule has an attribute
t.type. Other than this, rules are free to return any kind of token
object that they wish and may construct a new type of token object
from the attributes of t (provided the new object has the required
type attribute).
If illegal characters are encountered, the scanner executes the
function t_error(t) where t is a token representing the rest of the
string that hasn't been matched. If this function isn't defined, a
LexError exception is raised. The .text attribute of this exception
object contains the part of the string that wasn't matched.
The t.skip(n) method can be used to skip ahead n characters in the
input stream. This is usually only used in the error handling rule.
For instance, the following rule would print an error message and
continue:
def t_error(t):
print "Illegal character in input %s" % t.value[0]
t.skip(1)
Of course, a nice scanner might wish to skip more than one character
if the input looks very corrupted.
The lex module defines a t.lineno attribute on each token that can be used
to track the current line number in the input. The value of this
variable is not modified by lex so it is up to your lexer module
to correctly update its value depending on the lexical properties
of the input language. To do this, you might write rules such as
the following:
def t_newline(t):
r' \n+ '
t.lineno += t.value.count("\n")
To initialize your lexer so that it can be used, simply call the lex.lex()
function in your rule file. If there are any errors in your
specification, warning messages or an exception will be generated to
alert you to the problem.
(dave: this needs to be rewritten)
To use the newly constructed lexer from another module, simply do
this:
import lex
import lexer
plex.input("position = initial + rate*60")
while 1:
token = plex.token() # Get a token
if not token: break # No more tokens
... do whatever ...
Assuming that the module 'lexer' has initialized plex as shown
above, parsing modules can safely import 'plex' without having
to import the rule file or any additional imformation about the
scanner you have defined.
"""
# -----------------------------------------------------------------------------
__version__ = "1.3"
import re, types, sys, copy
# Exception thrown when invalid token encountered and no default
class LexError(Exception):
def __init__(self,message,s):
self.args = (message,)
self.text = s
# Token class
class LexToken:
def __str__(self):
return "LexToken(%s,%r,%d)" % (self.type,self.value,self.lineno)
def __repr__(self):
return str(self)
def skip(self,n):
try:
self._skipn += n
except AttributeError:
self._skipn = n
# -----------------------------------------------------------------------------
# Lexer class
#
# input() - Store a new string in the lexer
# token() - Get the next token
# -----------------------------------------------------------------------------
class Lexer:
def __init__(self):
self.lexre = None # Master regular expression
self.lexdata = None # Actual input data (as a string)
self.lexpos = 0 # Current position in input text
self.lexlen = 0 # Length of the input text
self.lexindexfunc = [ ] # Reverse mapping of groups to functions and types
self.lexerrorf = None # Error rule (if any)
self.lextokens = None # List of valid tokens
self.lexignore = None # Ignored characters
self.lineno = 1 # Current line number
self.debug = 0 # Debugging mode
self.optimize = 0 # Optimized mode
self.token = self.errtoken
def __copy__(self):
c = Lexer()
c.lexre = self.lexre
c.lexdata = self.lexdata
c.lexpos = self.lexpos
c.lexlen = self.lexlen
c.lenindexfunc = self.lexindexfunc
c.lexerrorf = self.lexerrorf
c.lextokens = self.lextokens
c.lexignore = self.lexignore
c.lineno = self.lineno
c.optimize = self.optimize
c.token = c.realtoken
# ------------------------------------------------------------
# input() - Push a new string into the lexer
# ------------------------------------------------------------
def input(self,s):
if not isinstance(s,types.StringType):
raise ValueError, "Expected a string"
self.lexdata = s
self.lexpos = 0
self.lexlen = len(s)
self.token = self.realtoken
# Change the token routine to point to realtoken()
global token
if token == self.errtoken:
token = self.token
# ------------------------------------------------------------
# errtoken() - Return error if token is called with no data
# ------------------------------------------------------------
def errtoken(self):
raise RuntimeError, "No input string given with input()"
# ------------------------------------------------------------
# token() - Return the next token from the Lexer
#
# Note: This function has been carefully implemented to be as fast
# as possible. Don't make changes unless you really know what
# you are doing
# ------------------------------------------------------------
def realtoken(self):
# Make local copies of frequently referenced attributes
lexpos = self.lexpos
lexlen = self.lexlen
lexignore = self.lexignore
lexdata = self.lexdata
while lexpos < lexlen:
# This code provides some short-circuit code for whitespace, tabs, and other ignored characters
if lexdata[lexpos] in lexignore:
lexpos += 1
continue
# Look for a regular expression match
m = self.lexre.match(lexdata,lexpos)
if m:
i = m.lastindex
lexpos = m.end()
tok = LexToken()
tok.value = m.group()
tok.lineno = self.lineno
tok.lexer = self
func,tok.type = self.lexindexfunc[i]
if not func:
self.lexpos = lexpos
return tok
# If token is processed by a function, call it
self.lexpos = lexpos
newtok = func(tok)
self.lineno = tok.lineno # Update line number
# Every function must return a token, if nothing, we just move to next token
if not newtok: continue
# Verify type of the token. If not in the token map, raise an error
if not self.optimize:
if not self.lextokens.has_key(newtok.type):
raise LexError, ("%s:%d: Rule '%s' returned an unknown token type '%s'" % (
func.func_code.co_filename, func.func_code.co_firstlineno,
func.__name__, newtok.type),lexdata[lexpos:])
return newtok
# No match. Call t_error() if defined.
if self.lexerrorf:
tok = LexToken()
tok.value = self.lexdata[lexpos:]
tok.lineno = self.lineno
tok.type = "error"
tok.lexer = self
oldpos = lexpos
newtok = self.lexerrorf(tok)
lexpos += getattr(tok,"_skipn",0)
if oldpos == lexpos:
# Error method didn't change text position at all. This is an error.
self.lexpos = lexpos
raise LexError, ("Scanning error. Illegal character '%s'" % (lexdata[lexpos]), lexdata[lexpos:])
if not newtok: continue
self.lexpos = lexpos
return newtok
self.lexpos = lexpos
raise LexError, ("No match found", lexdata[lexpos:])
# No more input data
self.lexpos = lexpos + 1
return None
# -----------------------------------------------------------------------------
# validate_file()
#
# This checks to see if there are duplicated t_rulename() functions or strings
# in the parser input file. This is done using a simple regular expression
# match on each line in the filename.
# -----------------------------------------------------------------------------
def validate_file(filename):
import os.path
base,ext = os.path.splitext(filename)
if ext != '.py': return 1 # No idea what the file is. Return OK
try:
f = open(filename)
lines = f.readlines()
f.close()
except IOError:
return 1 # Oh well
fre = re.compile(r'\s*def\s+(t_[a-zA-Z_0-9]*)\(')
sre = re.compile(r'\s*(t_[a-zA-Z_0-9]*)\s*=')
counthash = { }
linen = 1
noerror = 1
for l in lines:
m = fre.match(l)
if not m:
m = sre.match(l)
if m:
name = m.group(1)
prev = counthash.get(name)
if not prev:
counthash[name] = linen
else:
print "%s:%d: Rule %s redefined. Previously defined on line %d" % (filename,linen,name,prev)
noerror = 0
linen += 1
return noerror
# -----------------------------------------------------------------------------
# _read_lextab(module)
#
# Reads lexer table from a lextab file instead of using introspection.
# -----------------------------------------------------------------------------
def _read_lextab(lexer, fdict, module):
exec "import %s as lextab" % module
lexer.lexre = re.compile(lextab._lexre, re.VERBOSE)
lexer.lexindexfunc = lextab._lextab
for i in range(len(lextab._lextab)):
t = lexer.lexindexfunc[i]
if t:
if t[0]:
lexer.lexindexfunc[i] = (fdict[t[0]],t[1])
lexer.lextokens = lextab._lextokens
lexer.lexignore = lextab._lexignore
if lextab._lexerrorf:
lexer.lexerrorf = fdict[lextab._lexerrorf]
# -----------------------------------------------------------------------------
# lex(module)
#
# Build all of the regular expression rules from definitions in the supplied module
# -----------------------------------------------------------------------------
def lex(module=None,debug=0,optimize=0,lextab="lextab"):
ldict = None
regex = ""
error = 0
files = { }
lexer = Lexer()
lexer.debug = debug
lexer.optimize = optimize
global token,input
if module:
if not isinstance(module, types.ModuleType):
raise ValueError,"Expected a module"
ldict = module.__dict__
else:
# No module given. We might be able to get information from the caller.
try:
raise RuntimeError
except RuntimeError:
e,b,t = sys.exc_info()
f = t.tb_frame
f = f.f_back # Walk out to our calling function
ldict = f.f_globals # Grab its globals dictionary
if optimize and lextab:
try:
_read_lextab(lexer,ldict, lextab)
if not lexer.lexignore: lexer.lexignore = ""
token = lexer.token
input = lexer.input
return lexer
except ImportError:
pass
# Get the tokens map
tokens = ldict.get("tokens",None)
if not tokens:
raise SyntaxError,"lex: module does not define 'tokens'"
if not (isinstance(tokens,types.ListType) or isinstance(tokens,types.TupleType)):
raise SyntaxError,"lex: tokens must be a list or tuple."
# Build a dictionary of valid token names
lexer.lextokens = { }
if not optimize:
# Utility function for verifying tokens
def is_identifier(s):
for c in s:
if not (c.isalnum() or c == '_'): return 0
return 1
for n in tokens:
if not is_identifier(n):
print "lex: Bad token name '%s'" % n
error = 1
if lexer.lextokens.has_key(n):
print "lex: Warning. Token '%s' multiply defined." % n
lexer.lextokens[n] = None
else:
for n in tokens: lexer.lextokens[n] = None
if debug:
print "lex: tokens = '%s'" % lexer.lextokens.keys()
# Get a list of symbols with the t_ prefix
tsymbols = [f for f in ldict.keys() if f[:2] == 't_']
# Now build up a list of functions and a list of strings
fsymbols = [ ]
ssymbols = [ ]
for f in tsymbols:
if isinstance(ldict[f],types.FunctionType):
fsymbols.append(ldict[f])
elif isinstance(ldict[f],types.StringType):
ssymbols.append((f,ldict[f]))
else:
print "lex: %s not defined as a function or string" % f
error = 1
# Sort the functions by line number
fsymbols.sort(lambda x,y: cmp(x.func_code.co_firstlineno,y.func_code.co_firstlineno))
# Sort the strings by regular expression length
ssymbols.sort(lambda x,y: (len(x[1]) < len(y[1])) - (len(x[1]) > len(y[1])))
# Check for non-empty symbols
if len(fsymbols) == 0 and len(ssymbols) == 0:
raise SyntaxError,"lex: no rules of the form t_rulename are defined."
# Add all of the rules defined with actions first
for f in fsymbols:
line = f.func_code.co_firstlineno
file = f.func_code.co_filename
files[file] = None
if not optimize:
if f.func_code.co_argcount > 1:
print "%s:%d: Rule '%s' has too many arguments." % (file,line,f.__name__)
error = 1
continue
if f.func_code.co_argcount < 1:
print "%s:%d: Rule '%s' requires an argument." % (file,line,f.__name__)
error = 1
continue
if f.__name__ == 't_ignore':
print "%s:%d: Rule '%s' must be defined as a string." % (file,line,f.__name__)
error = 1
continue
if f.__name__ == 't_error':
lexer.lexerrorf = f
continue
if f.__doc__:
if not optimize:
try:
c = re.compile(f.__doc__, re.VERBOSE)
except re.error,e:
print "%s:%d: Invalid regular expression for rule '%s'. %s" % (file,line,f.__name__,e)
error = 1
continue
if debug:
print "lex: Adding rule %s -> '%s'" % (f.__name__,f.__doc__)
# Okay. The regular expression seemed okay. Let's append it to the master regular
# expression we're building
if (regex): regex += "|"
regex += "(?P<%s>%s)" % (f.__name__,f.__doc__)
else:
print "%s:%d: No regular expression defined for rule '%s'" % (file,line,f.__name__)
# Now add all of the simple rules
for name,r in ssymbols:
if name == 't_ignore':
lexer.lexignore = r
continue
if not optimize:
if name == 't_error':
raise SyntaxError,"lex: Rule 't_error' must be defined as a function"
error = 1
continue
if not lexer.lextokens.has_key(name[2:]):
print "lex: Rule '%s' defined for an unspecified token %s." % (name,name[2:])
error = 1
continue
try:
c = re.compile(r,re.VERBOSE)
except re.error,e:
print "lex: Invalid regular expression for rule '%s'. %s" % (name,e)
error = 1
continue
if debug:
print "lex: Adding rule %s -> '%s'" % (name,r)
if regex: regex += "|"
regex += "(?P<%s>%s)" % (name,r)
if not optimize:
for f in files.keys():
if not validate_file(f):
error = 1
try:
if debug:
print "lex: regex = '%s'" % regex
lexer.lexre = re.compile(regex, re.VERBOSE)
# Build the index to function map for the matching engine
lexer.lexindexfunc = [ None ] * (max(lexer.lexre.groupindex.values())+1)
for f,i in lexer.lexre.groupindex.items():
handle = ldict[f]
if isinstance(handle,types.FunctionType):
lexer.lexindexfunc[i] = (handle,handle.__name__[2:])
else:
# If rule was specified as a string, we build an anonymous
# callback function to carry out the action
lexer.lexindexfunc[i] = (None,f[2:])
# If a lextab was specified, we create a file containing the precomputed
# regular expression and index table
if lextab and optimize:
lt = open(lextab+".py","w")
lt.write("# %s.py. This file automatically created by PLY. Don't edit.\n" % lextab)
lt.write("_lexre = %s\n" % repr(regex))
lt.write("_lextab = [\n");
for i in range(0,len(lexer.lexindexfunc)):
t = lexer.lexindexfunc[i]
if t:
if t[0]:
lt.write(" ('%s',%s),\n"% (t[0].__name__, repr(t[1])))
else:
lt.write(" (None,%s),\n" % repr(t[1]))
else:
lt.write(" None,\n")
lt.write("]\n");
lt.write("_lextokens = %s\n" % repr(lexer.lextokens))
lt.write("_lexignore = %s\n" % repr(lexer.lexignore))
if (lexer.lexerrorf):
lt.write("_lexerrorf = %s\n" % repr(lexer.lexerrorf.__name__))
else:
lt.write("_lexerrorf = None\n")
lt.close()
except re.error,e:
print "lex: Fatal error. Unable to compile regular expression rules. %s" % e
error = 1
if error:
raise SyntaxError,"lex: Unable to build lexer."
if not lexer.lexerrorf:
print "lex: Warning. no t_error rule is defined."
if not lexer.lexignore: lexer.lexignore = ""
# Create global versions of the token() and input() functions
token = lexer.token
input = lexer.input
return lexer
# -----------------------------------------------------------------------------
# run()
#
# This runs the lexer as a main program
# -----------------------------------------------------------------------------
def runmain(lexer=None,data=None):
if not data:
try:
filename = sys.argv[1]
f = open(filename)
data = f.read()
f.close()
except IndexError:
print "Reading from standard input (type EOF to end):"
data = sys.stdin.read()
if lexer:
_input = lexer.input
else:
_input = input
_input(data)
if lexer:
_token = lexer.token
else:
_token = token
while 1:
tok = _token()
if not tok: break
print "(%s,'%s',%d)" % (tok.type, tok.value, tok.lineno)

4
ext/ply/ply/__init__.py Normal file
View file

@ -0,0 +1,4 @@
# PLY package
# Author: David Beazley (dave@dabeaz.com)
__all__ = ['lex','yacc']

867
ext/ply/ply/lex.py Normal file
View file

@ -0,0 +1,867 @@
#-----------------------------------------------------------------------------
# ply: lex.py
#
# Author: David M. Beazley (dave@dabeaz.com)
#
# Copyright (C) 2001-2007, David M. Beazley
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
# See the file COPYING for a complete copy of the LGPL.
#-----------------------------------------------------------------------------
__version__ = "2.3"
import re, sys, types
# Regular expression used to match valid token names
_is_identifier = re.compile(r'^[a-zA-Z0-9_]+$')
# Available instance types. This is used when lexers are defined by a class.
# It's a little funky because I want to preserve backwards compatibility
# with Python 2.0 where types.ObjectType is undefined.
try:
_INSTANCETYPE = (types.InstanceType, types.ObjectType)
except AttributeError:
_INSTANCETYPE = types.InstanceType
class object: pass # Note: needed if no new-style classes present
# Exception thrown when invalid token encountered and no default error
# handler is defined.
class LexError(Exception):
def __init__(self,message,s):
self.args = (message,)
self.text = s
# Token class
class LexToken(object):
def __str__(self):
return "LexToken(%s,%r,%d,%d)" % (self.type,self.value,self.lineno,self.lexpos)
def __repr__(self):
return str(self)
def skip(self,n):
self.lexer.skip(n)
# -----------------------------------------------------------------------------
# Lexer class
#
# This class encapsulates all of the methods and data associated with a lexer.
#
# input() - Store a new string in the lexer
# token() - Get the next token
# -----------------------------------------------------------------------------
class Lexer:
def __init__(self):
self.lexre = None # Master regular expression. This is a list of
# tuples (re,findex) where re is a compiled
# regular expression and findex is a list
# mapping regex group numbers to rules
self.lexretext = None # Current regular expression strings
self.lexstatere = {} # Dictionary mapping lexer states to master regexs
self.lexstateretext = {} # Dictionary mapping lexer states to regex strings
self.lexstate = "INITIAL" # Current lexer state
self.lexstatestack = [] # Stack of lexer states
self.lexstateinfo = None # State information
self.lexstateignore = {} # Dictionary of ignored characters for each state
self.lexstateerrorf = {} # Dictionary of error functions for each state
self.lexreflags = 0 # Optional re compile flags
self.lexdata = None # Actual input data (as a string)
self.lexpos = 0 # Current position in input text
self.lexlen = 0 # Length of the input text
self.lexerrorf = None # Error rule (if any)
self.lextokens = None # List of valid tokens
self.lexignore = "" # Ignored characters
self.lexliterals = "" # Literal characters that can be passed through
self.lexmodule = None # Module
self.lineno = 1 # Current line number
self.lexdebug = 0 # Debugging mode
self.lexoptimize = 0 # Optimized mode
def clone(self,object=None):
c = Lexer()
c.lexstatere = self.lexstatere
c.lexstateinfo = self.lexstateinfo
c.lexstateretext = self.lexstateretext
c.lexstate = self.lexstate
c.lexstatestack = self.lexstatestack
c.lexstateignore = self.lexstateignore
c.lexstateerrorf = self.lexstateerrorf
c.lexreflags = self.lexreflags
c.lexdata = self.lexdata
c.lexpos = self.lexpos
c.lexlen = self.lexlen
c.lextokens = self.lextokens
c.lexdebug = self.lexdebug
c.lineno = self.lineno
c.lexoptimize = self.lexoptimize
c.lexliterals = self.lexliterals
c.lexmodule = self.lexmodule
# If the object parameter has been supplied, it means we are attaching the
# lexer to a new object. In this case, we have to rebind all methods in
# the lexstatere and lexstateerrorf tables.
if object:
newtab = { }
for key, ritem in self.lexstatere.items():
newre = []
for cre, findex in ritem:
newfindex = []
for f in findex:
if not f or not f[0]:
newfindex.append(f)
continue
newfindex.append((getattr(object,f[0].__name__),f[1]))
newre.append((cre,newfindex))
newtab[key] = newre
c.lexstatere = newtab
c.lexstateerrorf = { }
for key, ef in self.lexstateerrorf.items():
c.lexstateerrorf[key] = getattr(object,ef.__name__)
c.lexmodule = object
# Set up other attributes
c.begin(c.lexstate)
return c
# ------------------------------------------------------------
# writetab() - Write lexer information to a table file
# ------------------------------------------------------------
def writetab(self,tabfile):
tf = open(tabfile+".py","w")
tf.write("# %s.py. This file automatically created by PLY (version %s). Don't edit!\n" % (tabfile,__version__))
tf.write("_lextokens = %s\n" % repr(self.lextokens))
tf.write("_lexreflags = %s\n" % repr(self.lexreflags))
tf.write("_lexliterals = %s\n" % repr(self.lexliterals))
tf.write("_lexstateinfo = %s\n" % repr(self.lexstateinfo))
tabre = { }
for key, lre in self.lexstatere.items():
titem = []
for i in range(len(lre)):
titem.append((self.lexstateretext[key][i],_funcs_to_names(lre[i][1])))
tabre[key] = titem
tf.write("_lexstatere = %s\n" % repr(tabre))
tf.write("_lexstateignore = %s\n" % repr(self.lexstateignore))
taberr = { }
for key, ef in self.lexstateerrorf.items():
if ef:
taberr[key] = ef.__name__
else:
taberr[key] = None
tf.write("_lexstateerrorf = %s\n" % repr(taberr))
tf.close()
# ------------------------------------------------------------
# readtab() - Read lexer information from a tab file
# ------------------------------------------------------------
def readtab(self,tabfile,fdict):
exec "import %s as lextab" % tabfile
self.lextokens = lextab._lextokens
self.lexreflags = lextab._lexreflags
self.lexliterals = lextab._lexliterals
self.lexstateinfo = lextab._lexstateinfo
self.lexstateignore = lextab._lexstateignore
self.lexstatere = { }
self.lexstateretext = { }
for key,lre in lextab._lexstatere.items():
titem = []
txtitem = []
for i in range(len(lre)):
titem.append((re.compile(lre[i][0],lextab._lexreflags),_names_to_funcs(lre[i][1],fdict)))
txtitem.append(lre[i][0])
self.lexstatere[key] = titem
self.lexstateretext[key] = txtitem
self.lexstateerrorf = { }
for key,ef in lextab._lexstateerrorf.items():
self.lexstateerrorf[key] = fdict[ef]
self.begin('INITIAL')
# ------------------------------------------------------------
# input() - Push a new string into the lexer
# ------------------------------------------------------------
def input(self,s):
if not (isinstance(s,types.StringType) or isinstance(s,types.UnicodeType)):
raise ValueError, "Expected a string"
self.lexdata = s
self.lexpos = 0
self.lexlen = len(s)
# ------------------------------------------------------------
# begin() - Changes the lexing state
# ------------------------------------------------------------
def begin(self,state):
if not self.lexstatere.has_key(state):
raise ValueError, "Undefined state"
self.lexre = self.lexstatere[state]
self.lexretext = self.lexstateretext[state]
self.lexignore = self.lexstateignore.get(state,"")
self.lexerrorf = self.lexstateerrorf.get(state,None)
self.lexstate = state
# ------------------------------------------------------------
# push_state() - Changes the lexing state and saves old on stack
# ------------------------------------------------------------
def push_state(self,state):
self.lexstatestack.append(self.lexstate)
self.begin(state)
# ------------------------------------------------------------
# pop_state() - Restores the previous state
# ------------------------------------------------------------
def pop_state(self):
self.begin(self.lexstatestack.pop())
# ------------------------------------------------------------
# current_state() - Returns the current lexing state
# ------------------------------------------------------------
def current_state(self):
return self.lexstate
# ------------------------------------------------------------
# skip() - Skip ahead n characters
# ------------------------------------------------------------
def skip(self,n):
self.lexpos += n
# ------------------------------------------------------------
# token() - Return the next token from the Lexer
#
# Note: This function has been carefully implemented to be as fast
# as possible. Don't make changes unless you really know what
# you are doing
# ------------------------------------------------------------
def token(self):
# Make local copies of frequently referenced attributes
lexpos = self.lexpos
lexlen = self.lexlen
lexignore = self.lexignore
lexdata = self.lexdata
while lexpos < lexlen:
# This code provides some short-circuit code for whitespace, tabs, and other ignored characters
if lexdata[lexpos] in lexignore:
lexpos += 1
continue
# Look for a regular expression match
for lexre,lexindexfunc in self.lexre:
m = lexre.match(lexdata,lexpos)
if not m: continue
# Set last match in lexer so that rules can access it if they want
self.lexmatch = m
# Create a token for return
tok = LexToken()
tok.value = m.group()
tok.lineno = self.lineno
tok.lexpos = lexpos
tok.lexer = self
lexpos = m.end()
i = m.lastindex
func,tok.type = lexindexfunc[i]
self.lexpos = lexpos
if not func:
# If no token type was set, it's an ignored token
if tok.type: return tok
break
# if func not callable, it means it's an ignored token
if not callable(func):
break
# If token is processed by a function, call it
newtok = func(tok)
# Every function must return a token, if nothing, we just move to next token
if not newtok:
lexpos = self.lexpos # This is here in case user has updated lexpos.
break
# Verify type of the token. If not in the token map, raise an error
if not self.lexoptimize:
if not self.lextokens.has_key(newtok.type):
raise LexError, ("%s:%d: Rule '%s' returned an unknown token type '%s'" % (
func.func_code.co_filename, func.func_code.co_firstlineno,
func.__name__, newtok.type),lexdata[lexpos:])
return newtok
else:
# No match, see if in literals
if lexdata[lexpos] in self.lexliterals:
tok = LexToken()
tok.value = lexdata[lexpos]
tok.lineno = self.lineno
tok.lexer = self
tok.type = tok.value
tok.lexpos = lexpos
self.lexpos = lexpos + 1
return tok
# No match. Call t_error() if defined.
if self.lexerrorf:
tok = LexToken()
tok.value = self.lexdata[lexpos:]
tok.lineno = self.lineno
tok.type = "error"
tok.lexer = self
tok.lexpos = lexpos
self.lexpos = lexpos
newtok = self.lexerrorf(tok)
if lexpos == self.lexpos:
# Error method didn't change text position at all. This is an error.
raise LexError, ("Scanning error. Illegal character '%s'" % (lexdata[lexpos]), lexdata[lexpos:])
lexpos = self.lexpos
if not newtok: continue
return newtok
self.lexpos = lexpos
raise LexError, ("Illegal character '%s' at index %d" % (lexdata[lexpos],lexpos), lexdata[lexpos:])
self.lexpos = lexpos + 1
if self.lexdata is None:
raise RuntimeError, "No input string given with input()"
return None
# -----------------------------------------------------------------------------
# _validate_file()
#
# This checks to see if there are duplicated t_rulename() functions or strings
# in the parser input file. This is done using a simple regular expression
# match on each line in the filename.
# -----------------------------------------------------------------------------
def _validate_file(filename):
import os.path
base,ext = os.path.splitext(filename)
if ext != '.py': return 1 # No idea what the file is. Return OK
try:
f = open(filename)
lines = f.readlines()
f.close()
except IOError:
return 1 # Oh well
fre = re.compile(r'\s*def\s+(t_[a-zA-Z_0-9]*)\(')
sre = re.compile(r'\s*(t_[a-zA-Z_0-9]*)\s*=')
counthash = { }
linen = 1
noerror = 1
for l in lines:
m = fre.match(l)
if not m:
m = sre.match(l)
if m:
name = m.group(1)
prev = counthash.get(name)
if not prev:
counthash[name] = linen
else:
print >>sys.stderr, "%s:%d: Rule %s redefined. Previously defined on line %d" % (filename,linen,name,prev)
noerror = 0
linen += 1
return noerror
# -----------------------------------------------------------------------------
# _funcs_to_names()
#
# Given a list of regular expression functions, this converts it to a list
# suitable for output to a table file
# -----------------------------------------------------------------------------
def _funcs_to_names(funclist):
result = []
for f in funclist:
if f and f[0]:
result.append((f[0].__name__,f[1]))
else:
result.append(f)
return result
# -----------------------------------------------------------------------------
# _names_to_funcs()
#
# Given a list of regular expression function names, this converts it back to
# functions.
# -----------------------------------------------------------------------------
def _names_to_funcs(namelist,fdict):
result = []
for n in namelist:
if n and n[0]:
result.append((fdict[n[0]],n[1]))
else:
result.append(n)
return result
# -----------------------------------------------------------------------------
# _form_master_re()
#
# This function takes a list of all of the regex components and attempts to
# form the master regular expression. Given limitations in the Python re
# module, it may be necessary to break the master regex into separate expressions.
# -----------------------------------------------------------------------------
def _form_master_re(relist,reflags,ldict,toknames):
if not relist: return []
regex = "|".join(relist)
try:
lexre = re.compile(regex,re.VERBOSE | reflags)
# Build the index to function map for the matching engine
lexindexfunc = [ None ] * (max(lexre.groupindex.values())+1)
for f,i in lexre.groupindex.items():
handle = ldict.get(f,None)
if type(handle) in (types.FunctionType, types.MethodType):
lexindexfunc[i] = (handle,toknames[handle.__name__])
elif handle is not None:
# If rule was specified as a string, we build an anonymous
# callback function to carry out the action
if f.find("ignore_") > 0:
lexindexfunc[i] = (None,None)
else:
lexindexfunc[i] = (None, toknames[f])
return [(lexre,lexindexfunc)],[regex]
except Exception,e:
m = int(len(relist)/2)
if m == 0: m = 1
llist, lre = _form_master_re(relist[:m],reflags,ldict,toknames)
rlist, rre = _form_master_re(relist[m:],reflags,ldict,toknames)
return llist+rlist, lre+rre
# -----------------------------------------------------------------------------
# def _statetoken(s,names)
#
# Given a declaration name s of the form "t_" and a dictionary whose keys are
# state names, this function returns a tuple (states,tokenname) where states
# is a tuple of state names and tokenname is the name of the token. For example,
# calling this with s = "t_foo_bar_SPAM" might return (('foo','bar'),'SPAM')
# -----------------------------------------------------------------------------
def _statetoken(s,names):
nonstate = 1
parts = s.split("_")
for i in range(1,len(parts)):
if not names.has_key(parts[i]) and parts[i] != 'ANY': break
if i > 1:
states = tuple(parts[1:i])
else:
states = ('INITIAL',)
if 'ANY' in states:
states = tuple(names.keys())
tokenname = "_".join(parts[i:])
return (states,tokenname)
# -----------------------------------------------------------------------------
# lex(module)
#
# Build all of the regular expression rules from definitions in the supplied module
# -----------------------------------------------------------------------------
def lex(module=None,object=None,debug=0,optimize=0,lextab="lextab",reflags=0,nowarn=0):
global lexer
ldict = None
stateinfo = { 'INITIAL' : 'inclusive'}
error = 0
files = { }
lexobj = Lexer()
lexobj.lexdebug = debug
lexobj.lexoptimize = optimize
global token,input
if nowarn: warn = 0
else: warn = 1
if object: module = object
if module:
# User supplied a module object.
if isinstance(module, types.ModuleType):
ldict = module.__dict__
elif isinstance(module, _INSTANCETYPE):
_items = [(k,getattr(module,k)) for k in dir(module)]
ldict = { }
for (i,v) in _items:
ldict[i] = v
else:
raise ValueError,"Expected a module or instance"
lexobj.lexmodule = module
else:
# No module given. We might be able to get information from the caller.
try:
raise RuntimeError
except RuntimeError:
e,b,t = sys.exc_info()
f = t.tb_frame
f = f.f_back # Walk out to our calling function
ldict = f.f_globals # Grab its globals dictionary
if optimize and lextab:
try:
lexobj.readtab(lextab,ldict)
token = lexobj.token
input = lexobj.input
lexer = lexobj
return lexobj
except ImportError:
pass
# Get the tokens, states, and literals variables (if any)
if (module and isinstance(module,_INSTANCETYPE)):
tokens = getattr(module,"tokens",None)
states = getattr(module,"states",None)
literals = getattr(module,"literals","")
else:
tokens = ldict.get("tokens",None)
states = ldict.get("states",None)
literals = ldict.get("literals","")
if not tokens:
raise SyntaxError,"lex: module does not define 'tokens'"
if not (isinstance(tokens,types.ListType) or isinstance(tokens,types.TupleType)):
raise SyntaxError,"lex: tokens must be a list or tuple."
# Build a dictionary of valid token names
lexobj.lextokens = { }
if not optimize:
for n in tokens:
if not _is_identifier.match(n):
print >>sys.stderr, "lex: Bad token name '%s'" % n
error = 1
if warn and lexobj.lextokens.has_key(n):
print >>sys.stderr, "lex: Warning. Token '%s' multiply defined." % n
lexobj.lextokens[n] = None
else:
for n in tokens: lexobj.lextokens[n] = None
if debug:
print "lex: tokens = '%s'" % lexobj.lextokens.keys()
try:
for c in literals:
if not (isinstance(c,types.StringType) or isinstance(c,types.UnicodeType)) or len(c) > 1:
print >>sys.stderr, "lex: Invalid literal %s. Must be a single character" % repr(c)
error = 1
continue
except TypeError:
print >>sys.stderr, "lex: Invalid literals specification. literals must be a sequence of characters."
error = 1
lexobj.lexliterals = literals
# Build statemap
if states:
if not (isinstance(states,types.TupleType) or isinstance(states,types.ListType)):
print >>sys.stderr, "lex: states must be defined as a tuple or list."
error = 1
else:
for s in states:
if not isinstance(s,types.TupleType) or len(s) != 2:
print >>sys.stderr, "lex: invalid state specifier %s. Must be a tuple (statename,'exclusive|inclusive')" % repr(s)
error = 1
continue
name, statetype = s
if not isinstance(name,types.StringType):
print >>sys.stderr, "lex: state name %s must be a string" % repr(name)
error = 1
continue
if not (statetype == 'inclusive' or statetype == 'exclusive'):
print >>sys.stderr, "lex: state type for state %s must be 'inclusive' or 'exclusive'" % name
error = 1
continue
if stateinfo.has_key(name):
print >>sys.stderr, "lex: state '%s' already defined." % name
error = 1
continue
stateinfo[name] = statetype
# Get a list of symbols with the t_ or s_ prefix
tsymbols = [f for f in ldict.keys() if f[:2] == 't_' ]
# Now build up a list of functions and a list of strings
funcsym = { } # Symbols defined as functions
strsym = { } # Symbols defined as strings
toknames = { } # Mapping of symbols to token names
for s in stateinfo.keys():
funcsym[s] = []
strsym[s] = []
ignore = { } # Ignore strings by state
errorf = { } # Error functions by state
if len(tsymbols) == 0:
raise SyntaxError,"lex: no rules of the form t_rulename are defined."
for f in tsymbols:
t = ldict[f]
states, tokname = _statetoken(f,stateinfo)
toknames[f] = tokname
if callable(t):
for s in states: funcsym[s].append((f,t))
elif (isinstance(t, types.StringType) or isinstance(t,types.UnicodeType)):
for s in states: strsym[s].append((f,t))
else:
print >>sys.stderr, "lex: %s not defined as a function or string" % f
error = 1
# Sort the functions by line number
for f in funcsym.values():
f.sort(lambda x,y: cmp(x[1].func_code.co_firstlineno,y[1].func_code.co_firstlineno))
# Sort the strings by regular expression length
for s in strsym.values():
s.sort(lambda x,y: (len(x[1]) < len(y[1])) - (len(x[1]) > len(y[1])))
regexs = { }
# Build the master regular expressions
for state in stateinfo.keys():
regex_list = []
# Add rules defined by functions first
for fname, f in funcsym[state]:
line = f.func_code.co_firstlineno
file = f.func_code.co_filename
files[file] = None
tokname = toknames[fname]
ismethod = isinstance(f, types.MethodType)
if not optimize:
nargs = f.func_code.co_argcount
if ismethod:
reqargs = 2
else:
reqargs = 1
if nargs > reqargs:
print >>sys.stderr, "%s:%d: Rule '%s' has too many arguments." % (file,line,f.__name__)
error = 1
continue
if nargs < reqargs:
print >>sys.stderr, "%s:%d: Rule '%s' requires an argument." % (file,line,f.__name__)
error = 1
continue
if tokname == 'ignore':
print >>sys.stderr, "%s:%d: Rule '%s' must be defined as a string." % (file,line,f.__name__)
error = 1
continue
if tokname == 'error':
errorf[state] = f
continue
if f.__doc__:
if not optimize:
try:
c = re.compile("(?P<%s>%s)" % (f.__name__,f.__doc__), re.VERBOSE | reflags)
if c.match(""):
print >>sys.stderr, "%s:%d: Regular expression for rule '%s' matches empty string." % (file,line,f.__name__)
error = 1
continue
except re.error,e:
print >>sys.stderr, "%s:%d: Invalid regular expression for rule '%s'. %s" % (file,line,f.__name__,e)
if '#' in f.__doc__:
print >>sys.stderr, "%s:%d. Make sure '#' in rule '%s' is escaped with '\\#'." % (file,line, f.__name__)
error = 1
continue
if debug:
print "lex: Adding rule %s -> '%s' (state '%s')" % (f.__name__,f.__doc__, state)
# Okay. The regular expression seemed okay. Let's append it to the master regular
# expression we're building
regex_list.append("(?P<%s>%s)" % (f.__name__,f.__doc__))
else:
print >>sys.stderr, "%s:%d: No regular expression defined for rule '%s'" % (file,line,f.__name__)
# Now add all of the simple rules
for name,r in strsym[state]:
tokname = toknames[name]
if tokname == 'ignore':
if "\\" in r:
print >>sys.stderr, "lex: Warning. %s contains a literal backslash '\\'" % name
ignore[state] = r
continue
if not optimize:
if tokname == 'error':
raise SyntaxError,"lex: Rule '%s' must be defined as a function" % name
error = 1
continue
if not lexobj.lextokens.has_key(tokname) and tokname.find("ignore_") < 0:
print >>sys.stderr, "lex: Rule '%s' defined for an unspecified token %s." % (name,tokname)
error = 1
continue
try:
c = re.compile("(?P<%s>%s)" % (name,r),re.VERBOSE | reflags)
if (c.match("")):
print >>sys.stderr, "lex: Regular expression for rule '%s' matches empty string." % name
error = 1
continue
except re.error,e:
print >>sys.stderr, "lex: Invalid regular expression for rule '%s'. %s" % (name,e)
if '#' in r:
print >>sys.stderr, "lex: Make sure '#' in rule '%s' is escaped with '\\#'." % name
error = 1
continue
if debug:
print "lex: Adding rule %s -> '%s' (state '%s')" % (name,r,state)
regex_list.append("(?P<%s>%s)" % (name,r))
if not regex_list:
print >>sys.stderr, "lex: No rules defined for state '%s'" % state
error = 1
regexs[state] = regex_list
if not optimize:
for f in files.keys():
if not _validate_file(f):
error = 1
if error:
raise SyntaxError,"lex: Unable to build lexer."
# From this point forward, we're reasonably confident that we can build the lexer.
# No more errors will be generated, but there might be some warning messages.
# Build the master regular expressions
for state in regexs.keys():
lexre, re_text = _form_master_re(regexs[state],reflags,ldict,toknames)
lexobj.lexstatere[state] = lexre
lexobj.lexstateretext[state] = re_text
if debug:
for i in range(len(re_text)):
print "lex: state '%s'. regex[%d] = '%s'" % (state, i, re_text[i])
# For inclusive states, we need to add the INITIAL state
for state,type in stateinfo.items():
if state != "INITIAL" and type == 'inclusive':
lexobj.lexstatere[state].extend(lexobj.lexstatere['INITIAL'])
lexobj.lexstateretext[state].extend(lexobj.lexstateretext['INITIAL'])
lexobj.lexstateinfo = stateinfo
lexobj.lexre = lexobj.lexstatere["INITIAL"]
lexobj.lexretext = lexobj.lexstateretext["INITIAL"]
# Set up ignore variables
lexobj.lexstateignore = ignore
lexobj.lexignore = lexobj.lexstateignore.get("INITIAL","")
# Set up error functions
lexobj.lexstateerrorf = errorf
lexobj.lexerrorf = errorf.get("INITIAL",None)
if warn and not lexobj.lexerrorf:
print >>sys.stderr, "lex: Warning. no t_error rule is defined."
# Check state information for ignore and error rules
for s,stype in stateinfo.items():
if stype == 'exclusive':
if warn and not errorf.has_key(s):
print >>sys.stderr, "lex: Warning. no error rule is defined for exclusive state '%s'" % s
if warn and not ignore.has_key(s) and lexobj.lexignore:
print >>sys.stderr, "lex: Warning. no ignore rule is defined for exclusive state '%s'" % s
elif stype == 'inclusive':
if not errorf.has_key(s):
errorf[s] = errorf.get("INITIAL",None)
if not ignore.has_key(s):
ignore[s] = ignore.get("INITIAL","")
# Create global versions of the token() and input() functions
token = lexobj.token
input = lexobj.input
lexer = lexobj
# If in optimize mode, we write the lextab
if lextab and optimize:
lexobj.writetab(lextab)
return lexobj
# -----------------------------------------------------------------------------
# runmain()
#
# This runs the lexer as a main program
# -----------------------------------------------------------------------------
def runmain(lexer=None,data=None):
if not data:
try:
filename = sys.argv[1]
f = open(filename)
data = f.read()
f.close()
except IndexError:
print "Reading from standard input (type EOF to end):"
data = sys.stdin.read()
if lexer:
_input = lexer.input
else:
_input = input
_input(data)
if lexer:
_token = lexer.token
else:
_token = token
while 1:
tok = _token()
if not tok: break
print "(%s,%r,%d,%d)" % (tok.type, tok.value, tok.lineno,tok.lexpos)
# -----------------------------------------------------------------------------
# @TOKEN(regex)
#
# This decorator function can be used to set the regex expression on a function
# when its docstring might need to be set in an alternative way
# -----------------------------------------------------------------------------
def TOKEN(r):
def set_doc(f):
f.__doc__ = r
return f
return set_doc
# Alternative spelling of the TOKEN decorator
Token = TOKEN

994
ext/ply/yacc.py → ext/ply/ply/yacc.py
View file

File diff suppressed because it is too large Load diff

27
ext/ply/setup.py Normal file
View file

@ -0,0 +1,27 @@
from distutils.core import setup
setup(name = "ply",
description="Python Lex & Yacc",
long_description = """
PLY is yet another implementation of lex and yacc for Python. Although several other
parsing tools are available for Python, there are several reasons why you might
want to take a look at PLY:
It's implemented entirely in Python.
It uses LR-parsing which is reasonably efficient and well suited for larger grammars.
PLY provides most of the standard lex/yacc features including support for empty
productions, precedence rules, error recovery, and support for ambiguous grammars.
PLY is extremely easy to use and provides very extensive error checking.
""",
license="""Lesser GPL (LGPL)""",
version = "2.3",
author = "David Beazley",
author_email = "dave@dabeaz.com",
maintainer = "David Beazley",
maintainer_email = "dave@dabeaz.com",
url = "http://www.dabeaz.com/ply/",
packages = ['ply'],
)

6
ext/ply/test/README
View file

@ -4,6 +4,8 @@ conditions. To run:
$ python testlex.py .
$ python testyacc.py .
(make sure lex.py and yacc.py exist in this directory before
running the tests).
The tests can also be run using the Python unittest module.
$ python rununit.py
The script 'cleanup.sh' cleans up this directory to its original state.

7
ext/ply/test/calclex.py
View file

@ -1,6 +1,10 @@
# -----------------------------------------------------------------------------
# calclex.py
# -----------------------------------------------------------------------------
import sys
sys.path.append("..")
import ply.lex as lex
tokens = (
'NAME','NUMBER',
@ -36,10 +40,9 @@ def t_newline(t):
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.skip(1)
t.lexer.skip(1)
# Build the lexer
import lex
lex.lex()

4
ext/ply/test/cleanup.sh Normal file
View file

@ -0,0 +1,4 @@
#!/bin/sh
rm -f *~ *.pyc *.dif *.out

2
ext/ply/test/lex_doc1.exp
View file

@ -1 +1 @@
./lex_doc1.py:15: No regular expression defined for rule 't_NUMBER'
./lex_doc1.py:18: No regular expression defined for rule 't_NUMBER'

5
ext/ply/test/lex_doc1.py
View file

@ -2,7 +2,10 @@
#
# Missing documentation string
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",

2
ext/ply/test/lex_dup1.exp
View file

@ -1,2 +1,2 @@
./lex_dup1.py:17: Rule t_NUMBER redefined. Previously defined on line 15
./lex_dup1.py:20: Rule t_NUMBER redefined. Previously defined on line 18
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_dup1.py
View file

@ -2,7 +2,10 @@
#
# Duplicated rule specifiers
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -19,7 +22,6 @@ t_NUMBER = r'\d+'
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

2
ext/ply/test/lex_dup2.exp
View file

@ -1,2 +1,2 @@
./lex_dup2.py:19: Rule t_NUMBER redefined. Previously defined on line 15
./lex_dup2.py:22: Rule t_NUMBER redefined. Previously defined on line 18
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_dup2.py
View file

@ -2,7 +2,10 @@
#
# Duplicated rule specifiers
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -23,7 +26,6 @@ def t_NUMBER(t):
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

2
ext/ply/test/lex_dup3.exp
View file

@ -1,2 +1,2 @@
./lex_dup3.py:17: Rule t_NUMBER redefined. Previously defined on line 15
./lex_dup3.py:20: Rule t_NUMBER redefined. Previously defined on line 18
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_dup3.py
View file

@ -2,7 +2,10 @@
#
# Duplicated rule specifiers
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -21,7 +24,6 @@ def t_NUMBER(t):
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

6
ext/ply/test/lex_empty.py
View file

@ -2,7 +2,10 @@
#
# No rules defined
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -10,7 +13,6 @@ tokens = [
"NUMBER",
]
import sys
sys.tracebacklimit = 0
lex.lex()

6
ext/ply/test/lex_error1.py
View file

@ -2,7 +2,10 @@
#
# Missing t_error() rule
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -14,7 +17,6 @@ t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
import sys
sys.tracebacklimit = 0
lex.lex()

6
ext/ply/test/lex_error2.py
View file

@ -2,7 +2,10 @@
#
# t_error defined, but not function
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -16,7 +19,6 @@ t_NUMBER = r'\d+'
t_error = "foo"
import sys
sys.tracebacklimit = 0
lex.lex()

2
ext/ply/test/lex_error3.exp
View file

@ -1,2 +1,2 @@
./lex_error3.py:17: Rule 't_error' requires an argument.
./lex_error3.py:20: Rule 't_error' requires an argument.
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_error3.py
View file

@ -2,7 +2,10 @@
#
# t_error defined as function, but with wrong # args
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -17,7 +20,6 @@ t_NUMBER = r'\d+'
def t_error():
pass
import sys
sys.tracebacklimit = 0
lex.lex()

2
ext/ply/test/lex_error4.exp
View file

@ -1,2 +1,2 @@
./lex_error4.py:17: Rule 't_error' has too many arguments.
./lex_error4.py:20: Rule 't_error' has too many arguments.
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_error4.py
View file

@ -2,7 +2,10 @@
#
# t_error defined as function, but too many args
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -17,7 +20,6 @@ t_NUMBER = r'\d+'
def t_error(t,s):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

6
ext/ply/test/lex_hedit.exp
View file

@ -1,3 +1,3 @@
(H_EDIT_DESCRIPTOR,'abc',1)
(H_EDIT_DESCRIPTOR,'abcdefghij',1)
(H_EDIT_DESCRIPTOR,'xy',1)
(H_EDIT_DESCRIPTOR,'abc',1,0)
(H_EDIT_DESCRIPTOR,'abcdefghij',1,6)
(H_EDIT_DESCRIPTOR,'xy',1,20)

7
ext/ply/test/lex_hedit.py
View file

@ -13,6 +13,10 @@
# This example shows how to modify the state of the lexer to parse
# such tokens
# -----------------------------------------------------------------------------
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = (
'H_EDIT_DESCRIPTOR',
@ -33,10 +37,9 @@ def t_H_EDIT_DESCRIPTOR(t):
def t_error(t):
print "Illegal character '%s'" % t.value[0]
t.skip(1)
t.lexer.skip(1)
# Build the lexer
import lex
lex.lex()
lex.runmain(data="3Habc 10Habcdefghij 2Hxy")

7
ext/ply/test/lex_ignore.exp
View file

@ -1,2 +1,7 @@
./lex_ignore.py:17: Rule 't_ignore' must be defined as a string.
./lex_ignore.py:20: Rule 't_ignore' must be defined as a string.
Traceback (most recent call last):
File "./lex_ignore.py", line 29, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_ignore.py
View file

@ -2,7 +2,10 @@
#
# Improperly specific ignore declaration
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -22,7 +25,6 @@ def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

1
ext/ply/test/lex_ignore2.exp Normal file
View file

@ -0,0 +1 @@
lex: Warning. t_ignore contains a literal backslash '\'

29
ext/ply/test/lex_ignore2.py Normal file
View file

@ -0,0 +1,29 @@
# lex_token.py
#
# ignore declaration as a raw string
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
t_ignore = r' \t'
def t_error(t):
pass
import sys
lex.lex()

30
ext/ply/test/lex_nowarn.py Normal file
View file

@ -0,0 +1,30 @@
# lex_token.py
#
# Missing t_error() rule
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
"NUMBER",
]
states = (('foo','exclusive'),)
t_ignore = ' \t'
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
t_foo_NUMBER = r'\d+'
sys.tracebacklimit = 0
lex.lex(nowarn=1)

5
ext/ply/test/lex_re1.exp
View file

@ -1,2 +1,7 @@
lex: Invalid regular expression for rule 't_NUMBER'. unbalanced parenthesis
Traceback (most recent call last):
File "./lex_re1.py", line 25, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

6
ext/ply/test/lex_re1.py
View file

@ -2,7 +2,10 @@
#
# Bad regular expression in a string
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -18,7 +21,6 @@ def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

7
ext/ply/test/lex_re2.exp Normal file
View file

@ -0,0 +1,7 @@
lex: Regular expression for rule 't_PLUS' matches empty string.
Traceback (most recent call last):
File "./lex_re2.py", line 25, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

27
ext/ply/test/lex_re2.py Normal file
View file

@ -0,0 +1,27 @@
# lex_token.py
#
# Regular expression rule matches empty string
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
t_PLUS = r'\+?'
t_MINUS = r'-'
t_NUMBER = r'(\d+)'
def t_error(t):
pass
import sys
lex.lex()

8
ext/ply/test/lex_re3.exp Normal file
View file

@ -0,0 +1,8 @@
lex: Invalid regular expression for rule 't_POUND'. unbalanced parenthesis
lex: Make sure '#' in rule 't_POUND' is escaped with '\#'.
Traceback (most recent call last):
File "./lex_re3.py", line 27, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

29
ext/ply/test/lex_re3.py Normal file
View file

@ -0,0 +1,29 @@
# lex_token.py
#
# Regular expression rule matches empty string
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
"POUND",
]
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'(\d+)'
t_POUND = r'#'
def t_error(t):
pass
import sys
lex.lex()

6
ext/ply/test/lex_rule1.py
View file

@ -2,7 +2,10 @@
#
# Rule defined as some other type
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -17,7 +20,6 @@ t_NUMBER = 1
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

7
ext/ply/test/lex_state1.exp Normal file
View file

@ -0,0 +1,7 @@
lex: states must be defined as a tuple or list.
Traceback (most recent call last):
File "./lex_state1.py", line 38, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

40
ext/ply/test/lex_state1.py Normal file
View file

@ -0,0 +1,40 @@
# lex_state1.py
#
# Bad state declaration
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
states = 'comment'
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

8
ext/ply/test/lex_state2.exp Normal file
View file

@ -0,0 +1,8 @@
lex: invalid state specifier 'comment'. Must be a tuple (statename,'exclusive|inclusive')
lex: invalid state specifier 'example'. Must be a tuple (statename,'exclusive|inclusive')
Traceback (most recent call last):
File "./lex_state2.py", line 38, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

40
ext/ply/test/lex_state2.py Normal file
View file

@ -0,0 +1,40 @@
# lex_state2.py
#
# Bad state declaration
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
states = ('comment','example')
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

8
ext/ply/test/lex_state3.exp Normal file
View file

@ -0,0 +1,8 @@
lex: state name 1 must be a string
lex: No rules defined for state 'example'
Traceback (most recent call last):
File "./lex_state3.py", line 40, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

42
ext/ply/test/lex_state3.py Normal file
View file

@ -0,0 +1,42 @@
# lex_state2.py
#
# Bad state declaration
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
comment = 1
states = ((comment, 'inclusive'),
('example', 'exclusive'))
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

7
ext/ply/test/lex_state4.exp Normal file
View file

@ -0,0 +1,7 @@
lex: state type for state comment must be 'inclusive' or 'exclusive'
Traceback (most recent call last):
File "./lex_state4.py", line 39, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

41
ext/ply/test/lex_state4.py Normal file
View file

@ -0,0 +1,41 @@
# lex_state2.py
#
# Bad state declaration
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
comment = 1
states = (('comment', 'exclsive'),)
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

7
ext/ply/test/lex_state5.exp Normal file
View file

@ -0,0 +1,7 @@
lex: state 'comment' already defined.
Traceback (most recent call last):
File "./lex_state5.py", line 40, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

42
ext/ply/test/lex_state5.py Normal file
View file

@ -0,0 +1,42 @@
# lex_state2.py
#
# Bad state declaration
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
comment = 1
states = (('comment', 'exclusive'),
('comment', 'exclusive'))
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

1
ext/ply/test/lex_state_noerror.exp Normal file
View file

@ -0,0 +1 @@
lex: Warning. no error rule is defined for exclusive state 'comment'

41
ext/ply/test/lex_state_noerror.py Normal file
View file

@ -0,0 +1,41 @@
# lex_state2.py
#
# Declaration of a state for which no rules are defined
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
comment = 1
states = (('comment', 'exclusive'),)
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

7
ext/ply/test/lex_state_norule.exp Normal file
View file

@ -0,0 +1,7 @@
lex: No rules defined for state 'example'
Traceback (most recent call last):
File "./lex_state_norule.py", line 40, in <module>
lex.lex()
File "../ply/lex.py", line 759, in lex
raise SyntaxError,"lex: Unable to build lexer."
SyntaxError: lex: Unable to build lexer.

42
ext/ply/test/lex_state_norule.py Normal file
View file

@ -0,0 +1,42 @@
# lex_state2.py
#
# Declaration of a state for which no rules are defined
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
comment = 1
states = (('comment', 'exclusive'),
('example', 'exclusive'))
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
import sys
lex.lex()

7
ext/ply/test/lex_state_try.exp Normal file
View file

@ -0,0 +1,7 @@
(NUMBER,'3',1,0)
(PLUS,'+',1,2)
(NUMBER,'4',1,4)
Entering comment state
comment body LexToken(body_part,'This is a comment */',1,9)
(PLUS,'+',1,30)
(NUMBER,'10',1,32)

48
ext/ply/test/lex_state_try.py Normal file
View file

@ -0,0 +1,48 @@
# lex_state2.py
#
# Declaration of a state for which no rules are defined
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
"MINUS",
"NUMBER",
]
comment = 1
states = (('comment', 'exclusive'),)
t_PLUS = r'\+'
t_MINUS = r'-'
t_NUMBER = r'\d+'
t_ignore = " \t"
# Comments
def t_comment(t):
r'/\*'
t.lexer.begin('comment')
print "Entering comment state"
def t_comment_body_part(t):
r'(.|\n)*\*/'
print "comment body", t
t.lexer.begin('INITIAL')
def t_error(t):
pass
t_comment_error = t_error
t_comment_ignore = t_ignore
import sys
lex.lex()
data = "3 + 4 /* This is a comment */ + 10"
lex.runmain(data=data)

6
ext/ply/test/lex_token1.py
View file

@ -2,7 +2,10 @@
#
# Tests for absence of tokens variable
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
t_PLUS = r'\+'
t_MINUS = r'-'
@ -11,7 +14,6 @@ t_NUMBER = r'\d+'
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

6
ext/ply/test/lex_token2.py
View file

@ -2,7 +2,10 @@
#
# Tests for tokens of wrong type
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = "PLUS MINUS NUMBER"
@ -13,7 +16,6 @@ t_NUMBER = r'\d+'
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

7
ext/ply/test/lex_token3.py
View file

@ -2,7 +2,10 @@
#
# tokens is right type, but is missing a token for one rule
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -16,7 +19,7 @@ t_NUMBER = r'\d+'
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

6
ext/ply/test/lex_token4.py
View file

@ -2,7 +2,10 @@
#
# Bad token name
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -18,7 +21,6 @@ t_NUMBER = r'\d+'
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

2
ext/ply/test/lex_token5.exp
View file

@ -1 +1 @@
lex.LexError: ./lex_token5.py:16: Rule 't_NUMBER' returned an unknown token type 'NUM'
ply.lex.LexError: ./lex_token5.py:19: Rule 't_NUMBER' returned an unknown token type 'NUM'

6
ext/ply/test/lex_token5.py
View file

@ -2,7 +2,10 @@
#
# Return a bad token name
import lex
import sys
sys.path.insert(0,"..")
import ply.lex as lex
tokens = [
"PLUS",
@ -21,7 +24,6 @@ def t_NUMBER(t):
def t_error(t):
pass
import sys
sys.tracebacklimit = 0
lex.lex()

62
ext/ply/test/rununit.py Normal file
View file

@ -0,0 +1,62 @@
#!/usr/bin/env python
'''Script to run all tests using python "unittest" module'''
__author__ = "Miki Tebeka <miki.tebeka@zoran.com>"
from unittest import TestCase, main, makeSuite, TestSuite
from os import popen, environ, remove
from glob import glob
from sys import executable, argv
from os.path import isfile, basename, splitext
# Add path to lex.py and yacc.py
environ["PYTHONPATH"] = ".."
class PLYTest(TestCase):
'''General test case for PLY test'''
def _runtest(self, filename):
'''Run a single test file an compare result'''
exp_file = filename.replace(".py", ".exp")
self.failUnless(isfile(exp_file), "can't find %s" % exp_file)
pipe = popen("%s %s 2>&1" % (executable, filename))
out = pipe.read().strip()
self.failUnlessEqual(out, open(exp_file).read().strip())
class LexText(PLYTest):
'''Testing Lex'''
pass
class YaccTest(PLYTest):
'''Testing Yacc'''
def tearDown(self):
'''Cleanup parsetab.py[c] file'''
for ext in (".py", ".pyc"):
fname = "parsetab%s" % ext
if isfile(fname):
remove(fname)
def add_test(klass, filename):
'''Add a test to TestCase class'''
def t(self):
self._runtest(filename)
# Test name is test_FILENAME without the ./ and without the .py
setattr(klass, "test_%s" % (splitext(basename(filename))[0]), t)
# Add lex tests
for file in glob("./lex_*.py"):
add_test(LexText, file)
lex_suite = makeSuite(LexText, "test_")
# Add yacc tests
for file in glob("./yacc_*.py"):
add_test(YaccTest, file)
yacc_suite = makeSuite(YaccTest, "test_")
# All tests suite
test_suite = TestSuite((lex_suite, yacc_suite))
if __name__ == "__main__":
main()

Some files were not shown because too many files have changed in this diff Show more