diff options
Diffstat (limited to 'ext/ply')
144 files changed, 7737 insertions, 1532 deletions
diff --git a/ext/ply/ANNOUNCE b/ext/ply/ANNOUNCE new file mode 100644 index 000000000..f40902021 --- /dev/null +++ b/ext/ply/ANNOUNCE @@ -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)
\ No newline at end of file diff --git a/ext/ply/CHANGES b/ext/ply/CHANGES index 9c7334066..d88f3e5d6 100644 --- a/ext/ply/CHANGES +++ b/ext/ply/CHANGES @@ -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 diff --git a/ext/ply/README b/ext/ply/README index 35b458d4c..6e246c2bd 100644 --- a/ext/ply/README +++ b/ext/ply/README @@ -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: @@ -232,16 +253,24 @@ 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 - - - - diff --git a/ext/ply/TODO b/ext/ply/TODO index b2978150d..7139d53d1 100644 --- a/ext/ply/TODO +++ b/ext/ply/TODO @@ -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. - -5. More tests in the test directory. - -6. Performance improvements and cleanup in yacc.py. +3. More tests in the test directory. -7. More documentation. +4. Performance improvements and cleanup in yacc.py. -8. Lots and lots of cleanup. +5. More documentation (?). diff --git a/ext/ply/doc/makedoc.py b/ext/ply/doc/makedoc.py new file mode 100644 index 000000000..3eed9bd74 --- /dev/null +++ b/ext/ply/doc/makedoc.py @@ -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) + + diff --git a/ext/ply/doc/ply.html b/ext/ply/doc/ply.html index 2596066fe..dba0c6288 100644 --- a/ext/ply/doc/ply.html +++ b/ext/ply/doc/ply.html @@ -5,70 +5,131 @@ <body bgcolor="#ffffff"> <h1>PLY (Python Lex-Yacc)</h1> - + <b> David M. Beazley <br> -Department of Computer Science <br> -University of Chicago <br> -Chicago, IL 60637 <br> -beazley@cs.uchicago.edu <br> +dave@dabeaz.com<br> </b> <p> -Documentation version: $Header: /home/stever/bk/newmem2/ext/ply/doc/ply.html 1.1 03/06/06 14:53:34-00:00 stever@ $ +<b>PLY Version: 2.3</b> +<p> + +<!-- INDEX --> +<div class="sectiontoc"> +<ul> +<li><a href="#ply_nn1">Introduction</a> +<li><a href="#ply_nn2">PLY Overview</a> +<li><a href="#ply_nn3">Lex</a> +<ul> +<li><a href="#ply_nn4">Lex Example</a> +<li><a href="#ply_nn5">The tokens list</a> +<li><a href="#ply_nn6">Specification of tokens</a> +<li><a href="#ply_nn7">Token values</a> +<li><a href="#ply_nn8">Discarded tokens</a> +<li><a href="#ply_nn9">Line numbers and positional information</a> +<li><a href="#ply_nn10">Ignored characters</a> +<li><a href="#ply_nn11">Literal characters</a> +<li><a href="#ply_nn12">Error handling</a> +<li><a href="#ply_nn13">Building and using the lexer</a> +<li><a href="#ply_nn14">The @TOKEN decorator</a> +<li><a href="#ply_nn15">Optimized mode</a> +<li><a href="#ply_nn16">Debugging</a> +<li><a href="#ply_nn17">Alternative specification of lexers</a> +<li><a href="#ply_nn18">Maintaining state</a> +<li><a href="#ply_nn19">Duplicating lexers</a> +<li><a href="#ply_nn20">Internal lexer state</a> +<li><a href="#ply_nn21">Conditional lexing and start conditions</a> +<li><a href="#ply_nn21">Miscellaneous Issues</a> +</ul> +<li><a href="#ply_nn22">Parsing basics</a> +<li><a href="#ply_nn23">Yacc reference</a> +<ul> +<li><a href="#ply_nn24">An example</a> +<li><a href="#ply_nn25">Combining Grammar Rule Functions</a> +<li><a href="#ply_nn26">Character Literals</a> +<li><a href="#ply_nn26">Empty Productions</a> +<li><a href="#ply_nn28">Changing the starting symbol</a> +<li><a href="#ply_nn27">Dealing With Ambiguous Grammars</a> +<li><a href="#ply_nn28">The parser.out file</a> +<li><a href="#ply_nn29">Syntax Error Handling</a> +<ul> +<li><a href="#ply_nn30">Recovery and resynchronization with error rules</a> +<li><a href="#ply_nn31">Panic mode recovery</a> +<li><a href="#ply_nn32">General comments on error handling</a> +</ul> +<li><a href="#ply_nn33">Line Number and Position Tracking</a> +<li><a href="#ply_nn34">AST Construction</a> +<li><a href="#ply_nn35">Embedded Actions</a> +<li><a href="#ply_nn36">Yacc implementation notes</a> +</ul> +<li><a href="#ply_nn37">Parser and Lexer State Management</a> +<li><a href="#ply_nn38">Using Python's Optimized Mode</a> +<li><a href="#ply_nn39">Where to go from here?</a> +</ul> +</div> +<!-- INDEX --> + -<h2>Introduction</h2> -PLY is a Python-only implementation of the popular compiler -construction tools lex and yacc. The implementation borrows ideas -from a number of previous efforts; most notably John Aycock's SPARK -toolkit. However, the overall flavor of the implementation is more -closely modeled after the C version of lex and yacc. The other -significant feature of PLY is that it provides extensive input -validation and error reporting--much more so than other Python parsing -tools. + + + +<H2><a name="ply_nn1"></a>1. Introduction</H2> + + +PLY is a pure-Python implementation of the popular compiler +construction tools lex and yacc. The main goal of PLY is to stay +fairly faithful to the way in which traditional lex/yacc tools work. +This includes supporting LALR(1) parsing as well as providing +extensive input validation, error reporting, and diagnostics. Thus, +if you've used yacc in another programming language, it should be +relatively straightforward to use PLY. <p> -Early versions of PLY were developed to support the Introduction to -Compilers Course at the University of Chicago. In this course, +Early versions of PLY were developed to support an Introduction to +Compilers Course I taught in 2001 at the University of Chicago. In this course, students built a fully functional compiler for a simple Pascal-like language. Their compiler, implemented entirely in Python, had to include lexical analysis, parsing, type checking, type inference, nested scoping, and code generation for the SPARC processor. Approximately 30 different compiler implementations were completed in -this course. Most of PLY's interface and operation has been motivated by common +this course. Most of PLY's interface and operation has been influenced by common usability problems encountered by students. <p> -Because PLY was primarily developed as an instructional tool, you will -find it to be <em>MUCH</em> more picky about token and grammar rule -specification than most other Python parsing tools. In part, this +Since PLY was primarily developed as an instructional tool, you will +find it to be fairly picky about token and grammar rule +specification. In part, this added formality is meant to catch common programming mistakes made by novice users. However, advanced users will also find such features to be useful when building complicated grammars for real programming -languages. It should also be noted that PLY does not provide much in the way -of bells and whistles (e.g., automatic construction of abstract syntax trees, -tree traversal, etc.). Instead, you will find a bare-bones, yet +languages. It should also be noted that PLY does not provide much in +the way of bells and whistles (e.g., automatic construction of +abstract syntax trees, tree traversal, etc.). Nor would I consider it +to be a parsing framework. Instead, you will find a bare-bones, yet fully capable lex/yacc implementation written entirely in Python. <p> The rest of this document assumes that you are somewhat familar with -parsing theory, syntax directed translation, and automatic tools such -as lex and yacc. If you are unfamilar with these topics, you will -probably want to consult an introductory text such as "Compilers: -Principles, Techniques, and Tools", by Aho, Sethi, and Ullman. "Lex -and Yacc" by John Levine may also be handy. +parsing theory, syntax directed translation, and the use of compiler +construction tools such as lex and yacc in other programming +languages. If you are unfamilar with these topics, you will probably +want to consult an introductory text such as "Compilers: Principles, +Techniques, and Tools", by Aho, Sethi, and Ullman. O'Reilly's "Lex +and Yacc" by John Levine may also be handy. In fact, the O'Reilly book can be +used as a reference for PLY as the concepts are virtually identical. + +<H2><a name="ply_nn2"></a>2. PLY Overview</H2> -<h2>PLY Overview</h2> -PLY consists of two separate tools; <tt>lex.py</tt> and -<tt>yacc.py</tt>. <tt>lex.py</tt> is used to break input text into a +PLY consists of two separate modules; <tt>lex.py</tt> and +<tt>yacc.py</tt>, both of which are found in a Python package +called <tt>ply</tt>. The <tt>lex.py</tt> module is used to break input text into a collection of tokens specified by a collection of regular expression rules. <tt>yacc.py</tt> is used to recognize language syntax that has -been specified in the form of a context free grammar. Currently, -<tt>yacc.py</tt> uses LR parsing and generates its parsing tables -using the SLR algorithm. LALR(1) parsing may be supported in a future -release. +been specified in the form of a context free grammar. <tt>yacc.py</tt> uses LR parsing and generates its parsing tables +using either the LALR(1) (the default) or SLR table generation algorithms. <p> The two tools are meant to work together. Specifically, @@ -78,32 +139,77 @@ input stream. <tt>yacc.py</tt> calls this repeatedly to retrieve tokens and invoke grammar rules. The output of <tt>yacc.py</tt> is often an Abstract Syntax Tree (AST). However, this is entirely up to the user. If desired, <tt>yacc.py</tt> can also be used to implement -simple one-pass compilers. +simple one-pass compilers. <p> Like its Unix counterpart, <tt>yacc.py</tt> provides most of the features you expect including extensive error checking, grammar validation, support for empty productions, error tokens, and ambiguity -resolution via precedence rules. The primary difference between -<tt>yacc.py</tt> and <tt>yacc</tt> is the use of SLR parsing instead -of LALR(1). Although this slightly restricts the types of grammars -than can be successfully parsed, it is sufficiently powerful to handle most -kinds of normal programming language constructs. +resolution via precedence rules. In fact, everything that is possible in traditional yacc +should be supported in PLY. <p> -Finally, it is important to note that PLY relies on reflection -(introspection) to build its lexers and parsers. Unlike traditional -lex/yacc which require a special input file that is converted into a -separate source file, the specifications given to PLY <em>are</em> -valid Python programs. This means that there are no extra source -files nor is there a special compiler construction step (e.g., running -yacc to generate Python code for the compiler). +The primary difference between +<tt>yacc.py</tt> and Unix <tt>yacc</tt> is that <tt>yacc.py</tt> +doesn't involve a separate code-generation process. +Instead, PLY relies on reflection (introspection) +to build its lexers and parsers. Unlike traditional lex/yacc which +require a special input file that is converted into a separate source +file, the specifications given to PLY <em>are</em> valid Python +programs. This means that there are no extra source files nor is +there a special compiler construction step (e.g., running yacc to +generate Python code for the compiler). Since the generation of the +parsing tables is relatively expensive, PLY caches the results and +saves them to a file. If no changes are detected in the input source, +the tables are read from the cache. Otherwise, they are regenerated. + +<H2><a name="ply_nn3"></a>3. Lex</H2> + + +<tt>lex.py</tt> is used to tokenize an input string. For example, suppose +you're writing a programming language and a user supplied the following input string: + +<blockquote> +<pre> +x = 3 + 42 * (s - t) +</pre> +</blockquote> -<h2>Lex Example</h2> +A tokenizer splits the string into individual tokens -<tt>lex.py</tt> is used to write tokenizers. To do this, each token -must be defined by a regular expression rule. The following file -implements a very simple lexer for tokenizing simple integer expressions: +<blockquote> +<pre> +'x','=', '3', '+', '42', '*', '(', 's', '-', 't', ')' +</pre> +</blockquote> + +Tokens are usually given names to indicate what they are. For example: + +<blockquote> +<pre> +'ID','EQUALS','NUMBER','PLUS','NUMBER','TIMES', +'LPAREN','ID','MINUS','ID','RPAREN' +</pre> +</blockquote> + +More specifically, the input is broken into pairs of token types and values. For example: + +<blockquote> +<pre> +('ID','x'), ('EQUALS','='), ('NUMBER','3'), +('PLUS','+'), ('NUMBER','42), ('TIMES','*'), +('LPAREN','('), ('ID','s'), ('MINUS','-'), +('ID','t'), ('RPAREN',')' +</pre> +</blockquote> + +The identification of tokens is typically done by writing a series of regular expression +rules. The next section shows how this is done using <tt>lex.py</tt>. + +<H3><a name="ply_nn4"></a>3.1 Lex Example</H3> + + +The following example shows how <tt>lex.py</tt> is used to write a simple tokenizer. <blockquote> <pre> @@ -113,7 +219,7 @@ implements a very simple lexer for tokenizing simple integer expressions: # tokenizer for a simple expression evaluator for # numbers and +,-,*,/ # ------------------------------------------------------------ -import lex +import ply.lex as lex # List of token names. This is always required tokens = ( @@ -147,7 +253,7 @@ def t_NUMBER(t): # Define a rule so we can track line numbers def t_newline(t): r'\n+' - t.lineno += len(t.value) + t.lexer.lineno += len(t.value) # A string containing ignored characters (spaces and tabs) t_ignore = ' \t' @@ -155,11 +261,18 @@ t_ignore = ' \t' # Error handling rule def t_error(t): print "Illegal character '%s'" % t.value[0] - t.skip(1) + t.lexer.skip(1) # Build the lexer lex.lex() +</pre> +</blockquote> +To use the lexer, you first need to feed it some input text using its <tt>input()</tt> method. After that, repeated calls to <tt>token()</tt> produce tokens. The following code shows how this works: + +<blockquote> +<pre> + # Test it out data = ''' 3 + 4 * 10 @@ -177,11 +290,76 @@ while 1: </pre> </blockquote> -In the example, the <tt>tokens</tt> list defines all of the possible -token names that can be produced by the lexer. This list is always required -and is used to perform a variety of validation checks. Following the <tt>tokens</tt> -list, regular expressions are written for each token. Each of these -rules are defined by making declarations with a special prefix <tt>t_</tt> to indicate that it +When executed, the example will produce the following output: + +<blockquote> +<pre> +$ python example.py +LexToken(NUMBER,3,2,1) +LexToken(PLUS,'+',2,3) +LexToken(NUMBER,4,2,5) +LexToken(TIMES,'*',2,7) +LexToken(NUMBER,10,2,10) +LexToken(PLUS,'+',3,14) +LexToken(MINUS,'-',3,16) +LexToken(NUMBER,20,3,18) +LexToken(TIMES,'*',3,20) +LexToken(NUMBER,2,3,21) +</pre> +</blockquote> + +The tokens returned by <tt>lex.token()</tt> are instances +of <tt>LexToken</tt>. This object has +attributes <tt>tok.type</tt>, <tt>tok.value</tt>, +<tt>tok.lineno</tt>, and <tt>tok.lexpos</tt>. The following code shows an example of +accessing these attributes: + +<blockquote> +<pre> +# Tokenize +while 1: + tok = lex.token() + if not tok: break # No more input + print tok.type, tok.value, tok.line, tok.lexpos +</pre> +</blockquote> + +The <tt>tok.type</tt> and <tt>tok.value</tt> attributes contain the +type and value of the token itself. +<tt>tok.line</tt> and <tt>tok.lexpos</tt> contain information about +the location of the token. <tt>tok.lexpos</tt> is the index of the +token relative to the start of the input text. + +<H3><a name="ply_nn5"></a>3.2 The tokens list</H3> + + +All lexers must provide a list <tt>tokens</tt> that defines all of the possible token +names that can be produced by the lexer. This list is always required +and is used to perform a variety of validation checks. The tokens list is also used by the +<tt>yacc.py</tt> module to identify terminals. + +<p> +In the example, the following code specified the token names: + +<blockquote> +<pre> +tokens = ( + 'NUMBER', + 'PLUS', + 'MINUS', + 'TIMES', + 'DIVIDE', + 'LPAREN', + 'RPAREN', +) +</pre> +</blockquote> + +<H3><a name="ply_nn6"></a>3.3 Specification of tokens</H3> + + +Each token is specified by writing a regular expression rule. Each of these rules are +are defined by making declarations with a special prefix <tt>t_</tt> to indicate that it defines a token. For simple tokens, the regular expression can be specified as strings such as this (note: Python raw strings are used since they are the most convenient way to write regular expression strings): @@ -194,7 +372,8 @@ t_PLUS = r'\+' In this case, the name following the <tt>t_</tt> must exactly match one of the names supplied in <tt>tokens</tt>. If some kind of action needs to be performed, -a token rule can be specified as a function. For example: +a token rule can be specified as a function. For example, this rule matches numbers and +converts the string into a Python integer. <blockquote> <pre> @@ -209,21 +388,157 @@ def t_NUMBER(t): </pre> </blockquote> -In this case, the regular expression rule is specified in the function documentation string. +When a function is used, the regular expression rule is specified in the function documentation string. The function always takes a single argument which is an instance of -<tt>LexToken</tt>. This object has attributes of <tt>t.type</tt> which is the token type, -<tt>t.value</tt> which is the lexeme, and <tt>t.lineno</tt> which is the current line number. +<tt>LexToken</tt>. This object has attributes of <tt>t.type</tt> which is the token type (as a string), +<tt>t.value</tt> which is the lexeme (the actual text matched), <tt>t.lineno</tt> which is the current line number, and <tt>t.lexpos</tt> which +is the position of the token relative to the beginning of the input text. By default, <tt>t.type</tt> is set to the name following the <tt>t_</tt> prefix. The action function can modify the contents of the <tt>LexToken</tt> object as appropriate. However, when it is done, the resulting token should be returned. If no value is returned by the action function, the token is simply discarded and the next token read. <p> -The rule <tt>t_newline()</tt> illustrates a regular expression rule -for a discarded token. In this case, a rule is written to match -newlines so that proper line number tracking can be performed. -By returning no value, the function causes the newline character to be -discarded. +Internally, <tt>lex.py</tt> uses the <tt>re</tt> module to do its patten matching. When building the master regular expression, +rules are added in the following order: +<p> +<ol> +<li>All tokens defined by functions are added in the same order as they appear in the lexer file. +<li>Tokens defined by strings are added next by sorting them in order of decreasing regular expression length (longer expressions +are added first). +</ol> +<p> +Without this ordering, it can be difficult to correctly match certain types of tokens. For example, if you +wanted to have separate tokens for "=" and "==", you need to make sure that "==" is checked first. By sorting regular +expressions in order of decreasing length, this problem is solved for rules defined as strings. For functions, +the order can be explicitly controlled since rules appearing first are checked first. + +<p> +To handle reserved words, it is usually easier to just match an identifier and do a special name lookup in a function +like this: + +<blockquote> +<pre> +reserved = { + 'if' : 'IF', + 'then' : 'THEN', + 'else' : 'ELSE', + 'while' : 'WHILE', + ... +} + +def t_ID(t): + r'[a-zA-Z_][a-zA-Z_0-9]*' + t.type = reserved.get(t.value,'ID') # Check for reserved words + return t +</pre> +</blockquote> + +This approach greatly reduces the number of regular expression rules and is likely to make things a little faster. + +<p> +<b>Note:</b> You should avoid writing individual rules for reserved words. For example, if you write rules like this, + +<blockquote> +<pre> +t_FOR = r'for' +t_PRINT = r'print' +</pre> +</blockquote> + +those rules will be triggered for identifiers that include those words as a prefix such as "forget" or "printed". This is probably not +what you want. + +<H3><a name="ply_nn7"></a>3.4 Token values</H3> + + +When tokens are returned by lex, they have a value that is stored in the <tt>value</tt> attribute. Normally, the value is the text +that was matched. However, the value can be assigned to any Python object. For instance, when lexing identifiers, you may +want to return both the identifier name and information from some sort of symbol table. To do this, you might write a rule like this: + +<blockquote> +<pre> +def t_ID(t): + ... + # Look up symbol table information and return a tuple + t.value = (t.value, symbol_lookup(t.value)) + ... + return t +</pre> +</blockquote> + +It is important to note that storing data in other attribute names is <em>not</em> recommended. The <tt>yacc.py</tt> module only exposes the +contents of the <tt>value</tt> attribute. Thus, accessing other attributes may be unnecessarily awkward. + +<H3><a name="ply_nn8"></a>3.5 Discarded tokens</H3> + + +To discard a token, such as a comment, simply define a token rule that returns no value. For example: + +<blockquote> +<pre> +def t_COMMENT(t): + r'\#.*' + pass + # No return value. Token discarded +</pre> +</blockquote> + +Alternatively, you can include the prefix "ignore_" in the token declaration to force a token to be ignored. For example: + +<blockquote> +<pre> +t_ignore_COMMENT = r'\#.*' +</pre> +</blockquote> + +Be advised that if you are ignoring many different kinds of text, you may still want to use functions since these provide more precise +control over the order in which regular expressions are matched (i.e., functions are matched in order of specification whereas strings are +sorted by regular expression length). + +<H3><a name="ply_nn9"></a>3.6 Line numbers and positional information</H3> + + +<p>By default, <tt>lex.py</tt> knows nothing about line numbers. This is because <tt>lex.py</tt> doesn't know anything +about what constitutes a "line" of input (e.g., the newline character or even if the input is textual data). +To update this information, you need to write a special rule. In the example, the <tt>t_newline()</tt> rule shows how to do this. + +<blockquote> +<pre> +# Define a rule so we can track line numbers +def t_newline(t): + r'\n+' + t.lexer.lineno += len(t.value) +</pre> +</blockquote> +Within the rule, the <tt>lineno</tt> attribute of the underlying lexer <tt>t.lexer</tt> is updated. +After the line number is updated, the token is simply discarded since nothing is returned. + +<p> +<tt>lex.py</tt> does not perform and kind of automatic column tracking. However, it does record positional +information related to each token in the <tt>lexpos</tt> attribute. Using this, it is usually possible to compute +column information as a separate step. For instance, just count backwards until you reach a newline. + +<blockquote> +<pre> +# Compute column. +# input is the input text string +# token is a token instance +def find_column(input,token): + i = token.lexpos + while i > 0: + if input[i] == '\n': break + i -= 1 + column = (token.lexpos - i)+1 + return column +</pre> +</blockquote> + +Since column information is often only useful in the context of error handling, calculating the column +position can be performed when needed as opposed to doing it for each token. + +<H3><a name="ply_nn10"></a>3.7 Ignored characters</H3> + <p> The special <tt>t_ignore</tt> rule is reserved by <tt>lex.py</tt> for characters @@ -234,12 +549,55 @@ similar to <tt>t_newline()</tt>, the use of <tt>t_ignore</tt> provides substanti lexing performance because it is handled as a special case and is checked in a much more efficient manner than the normal regular expression rules. +<H3><a name="ply_nn11"></a>3.8 Literal characters</H3> + + +<p> +Literal characters can be specified by defining a variable <tt>literals</tt> in your lexing module. For example: + +<blockquote> +<pre> +literals = [ '+','-','*','/' ] +</pre> +</blockquote> + +or alternatively + +<blockquote> +<pre> +literals = "+-*/" +</pre> +</blockquote> + +A literal character is simply a single character that is returned "as is" when encountered by the lexer. Literals are checked +after all of the defined regular expression rules. Thus, if a rule starts with one of the literal characters, it will always +take precedence. +<p> +When a literal token is returned, both its <tt>type</tt> and <tt>value</tt> attributes are set to the character itself. For example, <tt>'+'</tt>. + +<H3><a name="ply_nn12"></a>3.9 Error handling</H3> + + <p> Finally, the <tt>t_error()</tt> function is used to handle lexing errors that occur when illegal characters are detected. In this case, the <tt>t.value</tt> attribute contains the -rest of the input string that has not been tokenized. In the example, we simply print -the offending character and skip ahead one character by calling <tt>t.skip(1)</tt>. +rest of the input string that has not been tokenized. In the example, the error function +was defined as follows: + +<blockquote> +<pre> +# Error handling rule +def t_error(t): + print "Illegal character '%s'" % t.value[0] + t.lexer.skip(1) +</pre> +</blockquote> + +In this case, we simply print the offending character and skip ahead one character by calling <tt>t.lexer.skip(1)</tt>. + +<H3><a name="ply_nn13"></a>3.10 Building and using the lexer</H3> + <p> To build the lexer, the function <tt>lex.lex()</tt> is used. This function @@ -253,193 +611,733 @@ be used to control the lexer. None if the end of the input text has been reached. </ul> -The code at the bottom of the example shows how the lexer is actually used. When executed, -the following output will be produced: +If desired, the lexer can also be used as an object. The <tt>lex()</tt> returns a <tt>Lexer</tt> object that +can be used for this purpose. For example: <blockquote> <pre> -$ python example.py -LexToken(NUMBER,3,2) -LexToken(PLUS,'+',2) -LexToken(NUMBER,4,2) -LexToken(TIMES,'*',2) -LexToken(NUMBER,10,2) -LexToken(PLUS,'+',3) -LexToken(MINUS,'-',3) -LexToken(NUMBER,20,3) -LexToken(TIMES,'*',3) -LexToken(NUMBER,2,3) +lexer = lex.lex() +lexer.input(sometext) +while 1: + tok = lexer.token() + if not tok: break + print tok </pre> </blockquote> -<h2>Lex Implementation Notes</h2> - -<ul> -<li><tt>lex.py</tt> uses the <tt>re</tt> module to do its patten matching. When building the master regular expression, -rules are added in the following order: <p> -<ol> -<li>All tokens defined by functions are added in the same order as they appear in the lexer file. -<li>Tokens defined by strings are added by sorting them in order of decreasing regular expression length (longer expressions -are added first). -</ol> +This latter technique should be used if you intend to use multiple lexers in your application. Simply define each +lexer in its own module and use the object returned by <tt>lex()</tt> as appropriate. + <p> -Without this ordering, it can be difficult to correctly match certain types of tokens. For example, if you -wanted to have separate tokens for "=" and "==", you need to make sure that "==" is checked first. By sorting regular -expressions in order of decreasing length, this problem is solved for rules defined as strings. For functions, -the order can be explicitly controlled since rules appearing first are checked first. +Note: The global functions <tt>lex.input()</tt> and <tt>lex.token()</tt> are bound to the <tt>input()</tt> +and <tt>token()</tt> methods of the last lexer created by the lex module. -<P> -<li>The lexer requires input to be supplied as a single input string. Since most machines have more than enough memory, this -rarely presents a performance concern. However, it means that the lexer currently can't be used with streaming data -such as open files or sockets. This limitation is primarily a side-effect of using the <tt>re</tt> module. +<H3><a name="ply_nn14"></a>3.11 The @TOKEN decorator</H3> -<p> -<li> -To handle reserved words, it is usually easier to just match an identifier and do a special name lookup in a function -like this: + +In some applications, you may want to define build tokens from as a series of +more complex regular expression rules. For example: <blockquote> <pre> -reserved = { - 'if' : 'IF', - 'then' : 'THEN', - 'else' : 'ELSE', - 'while' : 'WHILE', - ... -} +digit = r'([0-9])' +nondigit = r'([_A-Za-z])' +identifier = r'(' + nondigit + r'(' + digit + r'|' + nondigit + r')*)' def t_ID(t): - r'[a-zA-Z_][a-zA-Z_0-9]*' - t.type = reserved.get(t.value,'ID') # Check for reserved words - return t + # want docstring to be identifier above. ????? + ... </pre> </blockquote> -<p> -<li>The lexer requires tokens to be defined as class instances with <tt>t.type</tt>, <tt>t.value</tt>, and <tt>t.lineno</tt> -attributes. By default, tokens are created as instances of the <tt>LexToken</tt> class defined internally to <tt>lex.py</tt>. -If desired, you can create new kinds of tokens provided that they have the three required attributes. However, -in practice, it is probably safer to stick with the default. - -<p> -<li>The only safe attribute for assigning token properties is <tt>t.value</tt>. In some cases, you may want to attach -a number of different properties to a token (e.g., symbol table entries for identifiers). To do this, replace <tt>t.value</tt> -with a tuple or class instance. For example: +In this case, we want the regular expression rule for <tt>ID</tt> to be one of the variables above. However, there is no +way to directly specify this using a normal documentation string. To solve this problem, you can use the <tt>@TOKEN</tt> +decorator. For example: <blockquote> <pre> +from ply.lex import TOKEN + +@TOKEN(identifier) def t_ID(t): ... - # For identifiers, create a (lexeme, symtab) tuple - t.value = (t.value, symbol_lookup(t.value)) - ... - return t </pre> </blockquote> -Although allowed, do NOT assign additional attributes to the token object. For example, +This will attach <tt>identifier</tt> to the docstring for <tt>t_ID()</tt> allowing <tt>lex.py</tt> to work normally. An alternative +approach this problem is to set the docstring directly like this: + <blockquote> <pre> def t_ID(t): ... - # Bad implementation of above - t.symtab = symbol_lookup(t.value) - ... + +t_ID.__doc__ = identifier +</pre> +</blockquote> + +<b>NOTE:</b> Use of <tt>@TOKEN</tt> requires Python-2.4 or newer. If you're concerned about backwards compatibility with older +versions of Python, use the alternative approach of setting the docstring directly. + +<H3><a name="ply_nn15"></a>3.12 Optimized mode</H3> + + +For improved performance, it may be desirable to use Python's +optimized mode (e.g., running Python with the <tt>-O</tt> +option). However, doing so causes Python to ignore documentation +strings. This presents special problems for <tt>lex.py</tt>. To +handle this case, you can create your lexer using +the <tt>optimize</tt> option as follows: + +<blockquote> +<pre> +lexer = lex.lex(optimize=1) </pre> </blockquote> -The reason you don't want to do this is that the <tt>yacc.py</tt> -module only provides public access to the <tt>t.value</tt> attribute of each token. -Therefore, any other attributes you assign are inaccessible (if you are familiar -with the internals of C lex/yacc, <tt>t.value</tt> is the same as <tt>yylval.tok</tt>). +Next, run Python in its normal operating mode. When you do +this, <tt>lex.py</tt> will write a file called <tt>lextab.py</tt> to +the current directory. This file contains all of the regular +expression rules and tables used during lexing. On subsequent +executions, +<tt>lextab.py</tt> will simply be imported to build the lexer. This +approach substantially improves the startup time of the lexer and it +works in Python's optimized mode. <p> -<li>To track line numbers, the lexer internally maintains a line -number variable. Each token automatically gets the value of the -current line number in the <tt>t.lineno</tt> attribute. To modify the -current line number, simply change the <tt>t.lineno</tt> attribute -in a function rule (as previously shown for -<tt>t_newline()</tt>). Even if the resulting token is discarded, -changes to the line number remain in effect for subsequent tokens. +To change the name of the lexer-generated file, use the <tt>lextab</tt> keyword argument. For example: + +<blockquote> +<pre> +lexer = lex.lex(optimize=1,lextab="footab") +</pre> +</blockquote> + +When running in optimized mode, it is important to note that lex disables most error checking. Thus, this is really only recommended +if you're sure everything is working correctly and you're ready to start releasing production code. + +<H3><a name="ply_nn16"></a>3.13 Debugging</H3> + + +For the purpose of debugging, you can run <tt>lex()</tt> in a debugging mode as follows: + +<blockquote> +<pre> +lexer = lex.lex(debug=1) +</pre> +</blockquote> + +This will result in a large amount of debugging information to be printed including all of the added rules and the master +regular expressions. + +In addition, <tt>lex.py</tt> comes with a simple main function which +will either tokenize input read from standard input or from a file specified +on the command line. To use it, simply put this in your lexer: + +<blockquote> +<pre> +if __name__ == '__main__': + lex.runmain() +</pre> +</blockquote> + +<H3><a name="ply_nn17"></a>3.14 Alternative specification of lexers</H3> + + +As shown in the example, lexers are specified all within one Python module. If you want to +put token rules in a different module from the one in which you invoke <tt>lex()</tt>, use the +<tt>module</tt> keyword argument. <p> -<li>To support multiple scanners in the same application, the <tt>lex.lex()</tt> function -actually returns a special <tt>Lexer</tt> object. This object has two methods -<tt>input()</tt> and <tt>token()</tt> that can be used to supply input and get tokens. For example: +For example, you might have a dedicated module that just contains +the token rules: + +<blockquote> +<pre> +# module: tokrules.py +# This module just contains the lexing rules + +# List of token names. This is always required +tokens = ( + 'NUMBER', + 'PLUS', + 'MINUS', + 'TIMES', + 'DIVIDE', + 'LPAREN', + 'RPAREN', +) + +# Regular expression rules for simple tokens +t_PLUS = r'\+' +t_MINUS = r'-' +t_TIMES = r'\*' +t_DIVIDE = r'/' +t_LPAREN = r'\(' +t_RPAREN = r'\)' + +# A regular expression rule with some action code +def t_NUMBER(t): + r'\d+' + try: + t.value = int(t.value) + except ValueError: + print "Line %d: Number %s is too large!" % (t.lineno,t.value) + t.value = 0 + return t + +# Define a rule so we can track line numbers +def t_newline(t): + r'\n+' + t.lexer.lineno += len(t.value) + +# A string containing ignored characters (spaces and tabs) +t_ignore = ' \t' + +# Error handling rule +def t_error(t): + print "Illegal character '%s'" % t.value[0] + t.lexer.skip(1) +</pre> +</blockquote> + +Now, if you wanted to build a tokenizer from these rules from within a different module, you would do the following (shown for Python interactive mode): <blockquote> <pre> +>>> import tokrules +>>> <b>lexer = lex.lex(module=tokrules)</b> +>>> lexer.input("3 + 4") +>>> lexer.token() +LexToken(NUMBER,3,1,1,0) +>>> lexer.token() +LexToken(PLUS,'+',1,2) +>>> lexer.token() +LexToken(NUMBER,4,1,4) +>>> lexer.token() +None +>>> +</pre> +</blockquote> + +The <tt>object</tt> option can be used to define lexers as a class instead of a module. For example: + +<blockquote> +<pre> +import ply.lex as lex + +class MyLexer: + # List of token names. This is always required + tokens = ( + 'NUMBER', + 'PLUS', + 'MINUS', + 'TIMES', + 'DIVIDE', + 'LPAREN', + 'RPAREN', + ) + + # Regular expression rules for simple tokens + t_PLUS = r'\+' + t_MINUS = r'-' + t_TIMES = r'\*' + t_DIVIDE = r'/' + t_LPAREN = r'\(' + t_RPAREN = r'\)' + + # A regular expression rule with some action code + # Note addition of self parameter since we're in a class + def t_NUMBER(self,t): + r'\d+' + try: + t.value = int(t.value) + except ValueError: + print "Line %d: Number %s is too large!" % (t.lineno,t.value) + t.value = 0 + return t + + # Define a rule so we can track line numbers + def t_newline(self,t): + r'\n+' + t.lexer.lineno += len(t.value) + + # A string containing ignored characters (spaces and tabs) + t_ignore = ' \t' + + # Error handling rule + def t_error(self,t): + print "Illegal character '%s'" % t.value[0] + t.lexer.skip(1) + + <b># Build the lexer + def build(self,**kwargs): + self.lexer = lex.lex(object=self, **kwargs)</b> + + # Test it output + def test(self,data): + self.lexer.input(data) + while 1: + tok = lexer.token() + if not tok: break + print tok + +# Build the lexer and try it out +m = MyLexer() +m.build() # Build the lexer +m.test("3 + 4") # Test it +</pre> +</blockquote> + +For reasons that are subtle, you should <em>NOT</em> invoke <tt>lex.lex()</tt> inside the <tt>__init__()</tt> method of your class. If you +do, it may cause bizarre behavior if someone tries to duplicate a lexer object. Keep reading. + +<H3><a name="ply_nn18"></a>3.15 Maintaining state</H3> + + +In your lexer, you may want to maintain a variety of state information. This might include mode settings, symbol tables, and other details. There are a few +different ways to handle this situation. First, you could just keep some global variables: + +<blockquote> +<pre> +num_count = 0 +def t_NUMBER(t): + r'\d+' + global num_count + num_count += 1 + try: + t.value = int(t.value) + except ValueError: + print "Line %d: Number %s is too large!" % (t.lineno,t.value) + t.value = 0 + return t +</pre> +</blockquote> + +Alternatively, you can store this information inside the Lexer object created by <tt>lex()</tt>. To this, you can use the <tt>lexer</tt> attribute +of tokens passed to the various rules. For example: + +<blockquote> +<pre> +def t_NUMBER(t): + r'\d+' + t.lexer.num_count += 1 # Note use of lexer attribute + try: + t.value = int(t.value) + except ValueError: + print "Line %d: Number %s is too large!" % (t.lineno,t.value) + t.value = 0 + return t + lexer = lex.lex() -lexer.input(sometext) -while 1: - tok = lexer.token() - if not tok: break - print tok +lexer.num_count = 0 # Set the initial count </pre> </blockquote> -The functions <tt>lex.input()</tt> and <tt>lex.token()</tt> are bound to the <tt>input()</tt> -and <tt>token()</tt> methods of the last lexer created by the lex module. +This latter approach has the advantage of storing information inside +the lexer itself---something that may be useful if multiple instances +of the same lexer have been created. However, it may also feel kind +of "hacky" to the purists. Just to put their mind at some ease, all +internal attributes of the lexer (with the exception of <tt>lineno</tt>) have names that are prefixed +by <tt>lex</tt> (e.g., <tt>lexdata</tt>,<tt>lexpos</tt>, etc.). Thus, +it should be perfectly safe to store attributes in the lexer that +don't have names starting with that prefix. + +<p> +A third approach is to define the lexer as a class as shown in the previous example: +<blockquote> +<pre> +class MyLexer: + ... + def t_NUMBER(self,t): + r'\d+' + self.num_count += 1 + try: + t.value = int(t.value) + except ValueError: + print "Line %d: Number %s is too large!" % (t.lineno,t.value) + t.value = 0 + return t + + def build(self, **kwargs): + self.lexer = lex.lex(object=self,**kwargs) + + def __init__(self): + self.num_count = 0 + +# Create a lexer +m = MyLexer() +lexer = lex.lex(object=m) +</pre> +</blockquote> + +The class approach may be the easiest to manage if your application is going to be creating multiple instances of the same lexer and +you need to manage a lot of state. + +<H3><a name="ply_nn19"></a>3.16 Duplicating lexers</H3> + + +<b>NOTE: I am thinking about deprecating this feature. Post comments on <a href="http://groups.google.com/group/ply-hack">ply-hack@googlegroups.com</a> or send me a private email at dave@dabeaz.com.</b> <p> -<li>To reduce compiler startup time and improve performance, the lexer can be built in optimized mode as follows: +If necessary, a lexer object can be quickly duplicated by invoking its <tt>clone()</tt> method. For example: <blockquote> <pre> -lex.lex(optimize=1) +lexer = lex.lex() +... +newlexer = lexer.clone() </pre> </blockquote> -When used, most error checking and validation is disabled. This provides a slight performance -gain while tokenizing and tends to chop a few tenths of a second off startup time. Since it disables -error checking, this mode is not the default and is not recommended during development. However, once -you have your compiler fully working, it is usually safe to disable the error checks. +When a lexer is cloned, the copy is identical to the original lexer, +including any input text. However, once created, different text can be +fed to the clone which can be used independently. This capability may +be useful in situations when you are writing a parser/compiler that +involves recursive or reentrant processing. For instance, if you +needed to scan ahead in the input for some reason, you could create a +clone and use it to look ahead. <p> -<li>You can enable some additional debugging by building the lexer like this: +The advantage of using <tt>clone()</tt> instead of reinvoking <tt>lex()</tt> is +that it is significantly faster. Namely, it is not necessary to re-examine all of the +token rules, build a regular expression, and construct internal tables. All of this +information can simply be reused in the new lexer. + +<p> +Special considerations need to be made when cloning a lexer that is defined as a class. Previous sections +showed an example of a class <tt>MyLexer</tt>. If you have the following code: <blockquote> <pre> -lex.lex(debug=1) +m = MyLexer() +a = lex.lex(object=m) # Create a lexer + +b = a.clone() # Clone the lexer </pre> </blockquote> +Then both <tt>a</tt> and <tt>b</tt> are going to be bound to the same +object <tt>m</tt>. If the object <tt>m</tt> contains internal state +related to lexing, this sharing may lead to quite a bit of confusion. To fix this, +the <tt>clone()</tt> method accepts an optional argument that can be used to supply a new object. This +can be used to clone the lexer and bind it to a new instance. For example: + +<blockquote> +<pre> +m = MyLexer() # Create a lexer +a = lex.lex(object=m) + +# Create a clone +n = MyLexer() # New instance of MyLexer +b = a.clone(n) # New lexer bound to n +</pre> +</blockquote> + +It may make sense to encapsulate all of this inside a method: + +<blockquote> +<pre> +class MyLexer: + ... + def clone(self): + c = MyLexer() # Create a new instance of myself + # Copy attributes from self to c as appropriate + ... + # Clone the lexer + c.lexer = self.lexer.clone(c) + return c +</pre> +</blockquote> + +The fact that a new instance of <tt>MyLexer</tt> may be created while cloning a lexer is the reason why you should never +invoke <tt>lex.lex()</tt> inside <tt>__init__()</tt>. If you do, the lexer will be rebuilt from scratch and you lose +all of the performance benefits of using <tt>clone()</tt> in the first place. + +<H3><a name="ply_nn20"></a>3.17 Internal lexer state</H3> + + +A Lexer object <tt>lexer</tt> has a number of internal attributes that may be useful in certain +situations. + <p> -<li>To help you debug your lexer, <tt>lex.py</tt> comes with a simple main program which will either -tokenize input read from standard input or from a file. To use it, simply put this in your lexer: +<tt>lexer.lexpos</tt> +<blockquote> +This attribute is an integer that contains the current position within the input text. If you modify +the value, it will change the result of the next call to <tt>token()</tt>. Within token rule functions, this points +to the first character <em>after</em> the matched text. If the value is modified within a rule, the next returned token will be +matched at the new position. +</blockquote> + +<p> +<tt>lexer.lineno</tt> +<blockquote> +The current value of the line number attribute stored in the lexer. This can be modified as needed to +change the line number. +</blockquote> + +<p> +<tt>lexer.lexdata</tt> +<blockquote> +The current input text stored in the lexer. This is the string passed with the <tt>input()</tt> method. It +would probably be a bad idea to modify this unless you really know what you're doing. +</blockquote> + +<P> +<tt>lexer.lexmatch</tt> +<blockquote> +This is the raw <tt>Match</tt> object returned by the Python <tt>re.match()</tt> function (used internally by PLY) for the +current token. If you have written a regular expression that contains named groups, you can use this to retrieve those values. +</blockquote> + +<H3><a name="ply_nn21"></a>3.18 Conditional lexing and start conditions</H3> + + +In advanced parsing applications, it may be useful to have different +lexing states. For instance, you may want the occurrence of a certain +token or syntactic construct to trigger a different kind of lexing. +PLY supports a feature that allows the underlying lexer to be put into +a series of different states. Each state can have its own tokens, +lexing rules, and so forth. The implementation is based largely on +the "start condition" feature of GNU flex. Details of this can be found +at <a +href="http://www.gnu.org/software/flex/manual/html_chapter/flex_11.html">http://www.gnu.org/software/flex/manual/html_chapter/flex_11.html.</a>. + +<p> +To define a new lexing state, it must first be declared. This is done by including a "states" declaration in your +lex file. For example: <blockquote> <pre> -if __name__ == '__main__': - lex.runmain() +states = ( + ('foo','exclusive'), + ('bar','inclusive'), +) </pre> </blockquote> -Then, run you lexer as a main program such as <tt>python mylex.py</tt> +This declaration declares two states, <tt>'foo'</tt> +and <tt>'bar'</tt>. States may be of two types; <tt>'exclusive'</tt> +and <tt>'inclusive'</tt>. An exclusive state completely overrides the +default behavior of the lexer. That is, lex will only return tokens +and apply rules defined specifically for that state. An inclusive +state adds additional tokens and rules to the default set of rules. +Thus, lex will return both the tokens defined by default in addition +to those defined for the inclusive state. + +<p> +Once a state has been declared, tokens and rules are declared by including the +state name in token/rule declaration. For example: + +<blockquote> +<pre> +t_foo_NUMBER = r'\d+' # Token 'NUMBER' in state 'foo' +t_bar_ID = r'[a-zA-Z_][a-zA-Z0-9_]*' # Token 'ID' in state 'bar' + +def t_foo_newline(t): + r'\n' + t.lexer.lineno += 1 +</pre> +</blockquote> + +A token can be declared in multiple states by including multiple state names in the declaration. For example: + +<blockquote> +<pre> +t_foo_bar_NUMBER = r'\d+' # Defines token 'NUMBER' in both state 'foo' and 'bar' +</pre> +</blockquote> + +Alternative, a token can be declared in all states using the 'ANY' in the name. + +<blockquote> +<pre> +t_ANY_NUMBER = r'\d+' # Defines a token 'NUMBER' in all states +</pre> +</blockquote> + +If no state name is supplied, as is normally the case, the token is associated with a special state <tt>'INITIAL'</tt>. For example, +these two declarations are identical: + +<blockquote> +<pre> +t_NUMBER = r'\d+' +t_INITIAL_NUMBER = r'\d+' +</pre> +</blockquote> + +<p> +States are also associated with the special <tt>t_ignore</tt> and <tt>t_error()</tt> declarations. For example, if a state treats +these differently, you can declare: + +<blockquote> +<pre> +t_foo_ignore = " \t\n" # Ignored characters for state 'foo' + +def t_bar_error(t): # Special error handler for state 'bar' + pass +</pre> +</blockquote> + +By default, lexing operates in the <tt>'INITIAL'</tt> state. This state includes all of the normally defined tokens. +For users who aren't using different states, this fact is completely transparent. If, during lexing or parsing, you want to change +the lexing state, use the <tt>begin()</tt> method. For example: + +<blockquote> +<pre> +def t_begin_foo(t): + r'start_foo' + t.lexer.begin('foo') # Starts 'foo' state +</pre> +</blockquote> + +To get out of a state, you use <tt>begin()</tt> to switch back to the initial state. For example: + +<blockquote> +<pre> +def t_foo_end(t): + r'end_foo' + t.lexer.begin('INITIAL') # Back to the initial state +</pre> +</blockquote> + +The management of states can also be done with a stack. For example: + +<blockquote> +<pre> +def t_begin_foo(t): + r'start_foo' + t.lexer.push_state('foo') # Starts 'foo' state + +def t_foo_end(t): + r'end_foo' + t.lexer.pop_state() # Back to the previous state +</pre> +</blockquote> + +<p> +The use of a stack would be useful in situations where there are many ways of entering a new lexing state and you merely want to go back +to the previous state afterwards. + +<P> +An example might help clarify. Suppose you were writing a parser and you wanted to grab sections of arbitrary C code enclosed by +curly braces. That is, whenever you encounter a starting brace '{', you want to read all of the enclosed code up to the ending brace '}' +and return it as a string. Doing this with a normal regular expression rule is nearly (if not actually) impossible. This is because braces can +be nested and can be included in comments and strings. Thus, simply matching up to the first matching '}' character isn't good enough. Here is how +you might use lexer states to do this: + +<blockquote> +<pre> +# Declare the state +states = ( + ('ccode','exclusive'), +) + +# Match the first {. Enter ccode state. +def t_ccode(t): + r'\{' + t.lexer.code_start = t.lexer.lexpos # Record the starting position + t.lexer.level = 1 # Initial brace level + t.lexer.begin('ccode') # Enter 'ccode' state + +# Rules for the ccode state +def t_ccode_lbrace(t): + r'\{' + t.lexer.level +=1 + +def t_ccode_rbrace(t): + r'\}' + t.lexer.level -=1 + + # If closing brace, return the code fragment + if t.lexer.level == 0: + t.value = t.lexer.lexdata[t.lexer.code_start:t.lexer.lexpos+1] + t.type = "CCODE" + t.lexer.lineno += t.value.count('\n') + t.lexer.begin('INITIAL') + return t + +# C or C++ comment (ignore) +def t_ccode_comment(t): + r'(/\*(.|\n)*?*/)|(//.*)' + pass + +# C string +def t_ccode_string(t): + r'\"([^\\\n]|(\\.))*?\"' + +# C character literal +def t_ccode_char(t): + r'\'([^\\\n]|(\\.))*?\'' + +# Any sequence of non-whitespace characters (not braces, strings) +def t_ccode_nonspace(t): + r'[^\s\{\}\'\"]+' + +# Ignored characters (whitespace) +t_ccode_ignore = " \t\n" + +# For bad characters, we just skip over it +def t_ccode_error(t): + t.lexer.skip(1) +</pre> +</blockquote> + +In this example, the occurrence of the first '{' causes the lexer to record the starting position and enter a new state <tt>'ccode'</tt>. A collection of rules then match +various parts of the input that follow (comments, strings, etc.). All of these rules merely discard the token (by not returning a value). +However, if the closing right brace is encountered, the rule <tt>t_ccode_rbrace</tt> collects all of the code (using the earlier recorded starting +position), stores it, and returns a token 'CCODE' containing all of that text. When returning the token, the lexing state is restored back to its +initial state. + +<H3><a name="ply_nn21"></a>3.19 Miscellaneous Issues</H3> + + +<P> +<li>The lexer requires input to be supplied as a single input string. Since most machines have more than enough memory, this +rarely presents a performance concern. However, it means that the lexer currently can't be used with streaming data +such as open files or sockets. This limitation is primarily a side-effect of using the <tt>re</tt> module. + +<p> +<li>The lexer should work properly with both Unicode strings given as token and pattern matching rules as +well as for input text. + +<p> +<li>If you need to supply optional flags to the re.compile() function, use the reflags option to lex. For example: + +<blockquote> +<pre> +lex.lex(reflags=re.UNICODE) +</pre> +</blockquote> <p> <li>Since the lexer is written entirely in Python, its performance is largely determined by that of the Python <tt>re</tt> module. Although the lexer has been written to be as efficient as possible, it's not -blazingly fast when used on very large input files. Sorry. If +blazingly fast when used on very large input files. If performance is concern, you might consider upgrading to the most recent version of Python, creating a hand-written lexer, or offloading -the lexer into a C extension module. In defense of <tt>lex.py</tt>, -it's performance is not <em>that</em> bad when used on reasonably -sized input files. For instance, lexing a 4700 line C program with -32000 input tokens takes about 20 seconds on a 200 Mhz PC. Obviously, -it will run much faster on a more speedy machine. +the lexer into a C extension module. +<p> +If you are going to create a hand-written lexer and you plan to use it with <tt>yacc.py</tt>, +it only needs to conform to the following requirements: + +<ul> +<li>It must provide a <tt>token()</tt> method that returns the next token or <tt>None</tt> if no more +tokens are available. +<li>The <tt>token()</tt> method must return an object <tt>tok</tt> that has <tt>type</tt> and <tt>value</tt> attributes. </ul> -<h2>Parsing basics</h2> +<H2><a name="ply_nn22"></a>4. Parsing basics</H2> + <tt>yacc.py</tt> is used to parse language syntax. Before showing an example, there are a few important bits of background that must be -mentioned. First, <tt>syntax</tt> is usually specified in terms of a -context free grammar (CFG). For example, if you wanted to parse +mentioned. First, <em>syntax</em> is usually specified in terms of a BNF grammar. +For example, if you wanted to parse simple arithmetic expressions, you might first write an unambiguous grammar specification like this: @@ -458,7 +1356,11 @@ factor : NUMBER </pre> </blockquote> -Next, the semantic behavior of a language is often specified using a +In the grammar, symbols such as <tt>NUMBER</tt>, <tt>+</tt>, <tt>-</tt>, <tt>*</tt>, and <tt>/</tt> are known +as <em>terminals</em> and correspond to raw input tokens. Identifiers such as <tt>term</tt> and <tt>factor</tt> refer to more +complex rules, typically comprised of a collection of tokens. These identifiers are known as <em>non-terminals</em>. +<P> +The semantic behavior of a language is often specified using a technique known as syntax directed translation. In syntax directed translation, attributes are attached to each symbol in a given grammar rule along with an action. Whenever a particular grammar rule is @@ -483,7 +1385,12 @@ factor : NUMBER factor.val = int(NUMBER.lexval) </pre> </blockquote> -Finally, Yacc uses a parsing technique known as LR-parsing or shift-reduce parsing. LR parsing is a +A good way to think about syntax directed translation is to simply think of each symbol in the grammar as some +kind of object. The semantics of the language are then expressed as a collection of methods/operations on these +objects. + +<p> +Yacc uses a parsing technique known as LR-parsing or shift-reduce parsing. LR parsing is a bottom up technique that tries to recognize the right-hand-side of various grammar rules. Whenever a valid right-hand-side is found in the input, the appropriate action code is triggered and the grammar symbols are replaced by the grammar symbol on the left-hand-side. @@ -534,12 +1441,18 @@ appropriate action is triggered (if defined). If the input token can't be shift any grammar rules, a syntax error has occurred and the parser must take some kind of recovery step (or bail out). <p> -It is important to note that the underlying implementation is actually built around a large finite-state machine -and some tables. The construction of these tables is quite complicated and beyond the scope of this discussion. +It is important to note that the underlying implementation is built around a large finite-state machine that is encoded +in a collection of tables. The construction of these tables is quite complicated and beyond the scope of this discussion. However, subtle details of this process explain why, in the example above, the parser chooses to shift a token onto the stack in step 9 rather than reducing the rule <tt>expr : expr + term</tt>. -<h2>Yacc example</h2> +<H2><a name="ply_nn23"></a>5. Yacc reference</H2> + + +This section describes how to use write parsers in PLY. + +<H3><a name="ply_nn24"></a>5.1 An example</H3> + Suppose you wanted to make a grammar for simple arithmetic expressions as previously described. Here is how you would do it with <tt>yacc.py</tt>: @@ -548,50 +1461,53 @@ how you would do it with <tt>yacc.py</tt>: <pre> # Yacc example -import yacc +import ply.yacc as yacc # Get the token map from the lexer. This is required. from calclex import tokens -def p_expression_plus(t): +def p_expression_plus(p): 'expression : expression PLUS term' - t[0] = t[1] + t[3] + p[0] = p[1] + p[3] -def p_expression_minus(t): +def p_expression_minus(p): 'expression : expression MINUS term' - t[0] = t[1] - t[3] + p[0] = p[1] - p[3] -def p_expression_term(t): +def p_expression_term(p): 'expression : term' - t[0] = t[1] + p[0] = p[1] -def p_term_times(t): +def p_term_times(p): 'term : term TIMES factor' - t[0] = t[1] * t[3] + p[0] = p[1] * p[3] -def p_term_div(t): +def p_term_div(p): 'term : term DIVIDE factor' - t[0] = t[1] / t[3] + p[0] = p[1] / p[3] -def p_term_factor(t): +def p_term_factor(p): 'term : factor' - t[0] = t[1] + p[0] = p[1] -def p_factor_num(t): +def p_factor_num(p): 'factor : NUMBER' - t[0] = t[1] + p[0] = p[1] -def p_factor_expr(t): +def p_factor_expr(p): 'factor : LPAREN expression RPAREN' - t[0] = t[2] + p[0] = p[2] # Error rule for syntax errors -def p_error(t): +def p_error(p): print "Syntax error in input!" # Build the parser yacc.yacc() +# Use this if you want to build the parser using SLR instead of LALR +# yacc.yacc(method="SLR") + while 1: try: s = raw_input('calc > ') @@ -604,39 +1520,45 @@ while 1: </blockquote> In this example, each grammar rule is defined by a Python function where the docstring to that function contains the -appropriate context-free grammar specification (an idea borrowed from John Aycock's SPARK toolkit). Each function accepts a single -argument <tt>t</tt> that is a sequence containing the values of each grammar symbol in the corresponding rule. The values of -<tt>t[i]</tt> are mapped to grammar symbols as shown here: +appropriate context-free grammar specification. Each function accepts a single +argument <tt>p</tt> that is a sequence containing the values of each grammar symbol in the corresponding rule. The values of +<tt>p[i]</tt> are mapped to grammar symbols as shown here: <blockquote> <pre> -def p_expression_plus(t): +def p_expression_plus(p): 'expression : expression PLUS term' # ^ ^ ^ ^ - # t[0] t[1] t[2] t[3] + # p[0] p[1] p[2] p[3] - t[0] = t[1] + t[3] + p[0] = p[1] + p[3] </pre> </blockquote> -For tokens, the "value" in the corresponding <tt>t[i]</tt> is the -<em>same</em> as the value of the <tt>t.value</tt> attribute assigned +For tokens, the "value" of the corresponding <tt>p[i]</tt> is the +<em>same</em> as the <tt>p.value</tt> attribute assigned in the lexer module. For non-terminals, the value is determined by -whatever is placed in <tt>t[0]</tt> when rules are reduced. This +whatever is placed in <tt>p[0]</tt> when rules are reduced. This value can be anything at all. However, it probably most common for the value to be a simple Python type, a tuple, or an instance. In this example, we are relying on the fact that the <tt>NUMBER</tt> token stores an integer value in its value field. All of the other rules simply perform various types of integer operations and store the result. +<P> +Note: The use of negative indices have a special meaning in yacc---specially <tt>p[-1]</tt> does +not have the same value as <tt>p[3]</tt> in this example. Please see the section on "Embedded Actions" for further +details. + <p> The first rule defined in the yacc specification determines the starting grammar symbol (in this case, a rule for <tt>expression</tt> appears first). Whenever the starting rule is reduced by the parser and no more input is available, parsing stops and the final value is returned (this value will be whatever the top-most rule -placed in <tt>t[0]</tt>). +placed in <tt>p[0]</tt>). Note: an alternative starting symbol can be specified using the <tt>start</tt> keyword argument to +<tt>yacc()</tt>. -<p>The <tt>p_error(t)</tt> rule is defined to catch syntax errors. See the error handling section +<p>The <tt>p_error(p)</tt> rule is defined to catch syntax errors. See the error handling section below for more detail. <p> @@ -648,7 +1570,7 @@ such as this: <blockquote> <pre> $ python calcparse.py -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... calc > </pre> </blockquote> @@ -660,7 +1582,7 @@ debugging file called <tt>parser.out</tt> is created. On subsequent executions, <tt>yacc</tt> will reload the table from <tt>parsetab.py</tt> unless it has detected a change in the underlying grammar (in which case the tables and <tt>parsetab.py</tt> file are -regenerated). +regenerated). Note: The names of parser output files can be changed if necessary. See the notes that follow later. <p> If any errors are detected in your grammar specification, <tt>yacc.py</tt> will produce @@ -677,20 +1599,21 @@ diagnostic messages and possibly raise an exception. Some of the errors that ca The next few sections now discuss a few finer points of grammar construction. -<h2>Combining Grammar Rule Functions</h2> +<H3><a name="ply_nn25"></a>5.2 Combining Grammar Rule Functions</H3> + When grammar rules are similar, they can be combined into a single function. For example, consider the two rules in our earlier example: <blockquote> <pre> -def p_expression_plus(t): +def p_expression_plus(p): 'expression : expression PLUS term' - t[0] = t[1] + t[3] + p[0] = p[1] + p[3] def p_expression_minus(t): 'expression : expression MINUS term' - t[0] = t[1] - t[3] + p[0] = p[1] - p[3] </pre> </blockquote> @@ -698,13 +1621,13 @@ Instead of writing two functions, you might write a single function like this: <blockquote> <pre> -def p_expression(t): +def p_expression(p): '''expression : expression PLUS term | expression MINUS term''' - if 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] </pre> </blockquote> @@ -713,33 +1636,82 @@ have also been legal (although possibly confusing) to write this: <blockquote> <pre> -def p_binary_operators(t): +def p_binary_operators(p): '''expression : expression PLUS term | expression MINUS term term : term TIMES factor | term DIVIDE factor''' - 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] </pre> </blockquote> When combining grammar rules into a single function, it is usually a good idea for all of the rules to have a similar structure (e.g., the same number of terms). Otherwise, the corresponding action code may be more -complicated than necessary. +complicated than necessary. However, it is possible to handle simple cases using len(). For example: + +<blockquote> +<pre> +def p_expressions(p): + '''expression : expression MINUS expression + | MINUS expression''' + if (len(p) == 4): + p[0] = p[1] - p[3] + elif (len(p) == 3): + p[0] = -p[2] +</pre> +</blockquote> + +<H3><a name="ply_nn26"></a>5.3 Character Literals</H3> + + +If desired, a grammar may contain tokens defined as single character literals. For example: + +<blockquote> +<pre> +def p_binary_operators(p): + '''expression : expression '+' term + | expression '-' term + term : term '*' factor + | term '/' factor''' + 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] +</pre> +</blockquote> + +A character literal must be enclosed in quotes such as <tt>'+'</tt>. In addition, if literals are used, they must be declared in the +corresponding <tt>lex</tt> file through the use of a special <tt>literals</tt> declaration. + +<blockquote> +<pre> +# Literals. Should be placed in module given to lex() +literals = ['+','-','*','/' ] +</pre> +</blockquote> + +<b>Character literals are limited to a single character</b>. Thus, it is not legal to specify literals such as <tt>'<='</tt> or <tt>'=='</tt>. For this, use +the normal lexing rules (e.g., define a rule such as <tt>t_EQ = r'=='</tt>). + +<H3><a name="ply_nn26"></a>5.4 Empty Productions</H3> -<h2>Empty Productions</h2> <tt>yacc.py</tt> can handle empty productions by defining a rule like this: <blockquote> <pre> -def p_empty(t): +def p_empty(p): 'empty :' pass </pre> @@ -749,14 +1721,47 @@ Now to use the empty production, simply use 'empty' as a symbol. For example: <blockquote> <pre> -def p_optitem(t): +def p_optitem(p): 'optitem : item' ' | empty' ... </pre> </blockquote> -<h2>Dealing With Ambiguous Grammars</h2> +Note: You can write empty rules anywhere by simply specifying an empty right hand side. However, I personally find that +writing an "empty" rule and using "empty" to denote an empty production is easier to read. + +<H3><a name="ply_nn28"></a>5.5 Changing the starting symbol</H3> + + +Normally, the first rule found in a yacc specification defines the starting grammar rule (top level rule). To change this, simply +supply a <tt>start</tt> specifier in your file. For example: + +<blockquote> +<pre> +start = 'foo' + +def p_bar(p): + 'bar : A B' + +# This is the starting rule due to the start specifier above +def p_foo(p): + 'foo : bar X' +... +</pre> +</blockquote> + +The use of a <tt>start</tt> specifier may be useful during debugging since you can use it to have yacc build a subset of +a larger grammar. For this purpose, it is also possible to specify a starting symbol as an argument to <tt>yacc()</tt>. For example: + +<blockquote> +<pre> +yacc.yacc(start='foo') +</pre> +</blockquote> + +<H3><a name="ply_nn27"></a>5.6 Dealing With Ambiguous Grammars</H3> + The expression grammar given in the earlier example has been written in a special format to eliminate ambiguity. However, in many situations, it is extremely difficult or awkward to write grammars in this format. A @@ -775,7 +1780,7 @@ expression : expression PLUS expression Unfortunately, this grammar specification is ambiguous. For example, if you are parsing the string "3 * 4 + 5", there is no way to tell how the operators are supposed to be grouped. -For example, does this expression mean "(3 * 4) + 5" or is it "3 * (4+5)"? +For example, does the expression mean "(3 * 4) + 5" or is it "3 * (4+5)"? <p> When an ambiguous grammar is given to <tt>yacc.py</tt> it will print messages about "shift/reduce conflicts" @@ -796,7 +1801,7 @@ Step Symbol Stack Input Tokens Action </pre> </blockquote> -In this case, when the parser reaches step 6, it has two options. One is the reduce the +In this case, when the parser reaches step 6, it has two options. One is to reduce the rule <tt>expr : expr * expr</tt> on the stack. The other option is to shift the token <tt>+</tt> on the stack. Both options are perfectly legal from the rules of the context-free-grammar. @@ -806,7 +1811,7 @@ By default, all shift/reduce conflicts are resolved in favor of shifting. There example, the parser will always shift the <tt>+</tt> instead of reducing. Although this strategy works in many cases (including the ambiguous if-then-else), it is not enough for arithmetic expressions. In fact, in the above example, the decision to shift <tt>+</tt> is completely wrong---we should have -reduced <tt>expr * expr</tt> since multiplication has higher precedence than addition. +reduced <tt>expr * expr</tt> since multiplication has higher mathematical precedence than addition. <p>To resolve ambiguity, especially in expression grammars, <tt>yacc.py</tt> allows individual tokens to be assigned a precedence level and associativity. This is done by adding a variable @@ -823,25 +1828,37 @@ precedence = ( This declaration specifies that <tt>PLUS</tt>/<tt>MINUS</tt> have the same precedence level and are left-associative and that -<tt>TIMES</tt>/<tt>DIVIDE</tt> have the same precedence and are left-associative. -Furthermore, the declaration specifies that <tt>TIMES</tt>/<tt>DIVIDE</tt> have higher +<tt>TIMES</tt>/<tt>DIVIDE</tt> have the same precedence and are left-associative. +Within the <tt>precedence</tt> declaration, tokens are ordered from lowest to highest precedence. Thus, +this declaration specifies that <tt>TIMES</tt>/<tt>DIVIDE</tt> have higher precedence than <tt>PLUS</tt>/<tt>MINUS</tt> (since they appear later in the precedence specification). <p> -The precedence specification is used to attach a numerical precedence value and associativity direction -to each grammar rule. This is always determined by the precedence of the right-most terminal symbol. Therefore, -if PLUS/MINUS had a precedence of 1 and TIMES/DIVIDE had a precedence of 2, the grammar rules -would have precedence values as follows: +The precedence specification works by associating a numerical precedence level value and associativity direction to +the listed tokens. For example, in the above example you get: <blockquote> <pre> -expression : expression PLUS expression # prec = 1, left - | expression MINUS expression # prec = 1, left - | expression TIMES expression # prec = 2, left - | expression DIVIDE expression # prec = 2, left - | LPAREN expression RPAREN # prec = unknown - | NUMBER # prec = unknown +PLUS : level = 1, assoc = 'left' +MINUS : level = 1, assoc = 'left' +TIMES : level = 2, assoc = 'left' +DIVIDE : level = 2, assoc = 'left' +</pre> +</blockquote> + +These values are then used to attach a numerical precedence value and associativity direction +to each grammar rule. <em>This is always determined by looking at the precedence of the right-most terminal symbol.</em> +For example: + +<blockquote> +<pre> +expression : expression PLUS expression # level = 1, left + | expression MINUS expression # level = 1, left + | expression TIMES expression # level = 2, left + | expression DIVIDE expression # level = 2, left + | LPAREN expression RPAREN # level = None (not specified) + | NUMBER # level = None (not specified) </pre> </blockquote> @@ -858,6 +1875,11 @@ rule is reduced for left associativity, whereas the token is shifted for right a favor of shifting (the default). </ol> +For example, if "expression PLUS expression" has been parsed and the next token +is "TIMES", the action is going to be a shift because "TIMES" has a higher precedence level than "PLUS". On the other +hand, if "expression TIMES expression" has been parsed and the next token is "PLUS", the action +is going to be reduce because "PLUS" has a lower precedence than "TIMES." + <p> When shift/reduce conflicts are resolved using the first three techniques (with the help of precedence rules), <tt>yacc.py</tt> will report no errors or conflicts in the grammar. @@ -883,9 +1905,9 @@ Now, in the grammar file, we can write our unary minus rule like this: <blockquote> <pre> -def p_expr_uminus(t): +def p_expr_uminus(p): 'expression : MINUS expression %prec UMINUS' - t[0] = -t[2] + p[0] = -p[2] </pre> </blockquote> @@ -893,9 +1915,15 @@ In this case, <tt>%prec UMINUS</tt> overrides the default rule precedence--setti of UMINUS in the precedence specifier. <p> +At first, the use of UMINUS in this example may appear very confusing. +UMINUS is not an input token or a grammer rule. Instead, you should +think of it as the name of a special marker in the precedence table. When you use the <tt>%prec</tt> qualifier, you're simply +telling yacc that you want the precedence of the expression to be the same as for this special marker instead of the usual precedence. + +<p> It is also possible to specify non-associativity in the <tt>precedence</tt> table. This would be used when you <em>don't</em> want operations to chain together. For example, suppose -you wanted to support a comparison operators like <tt><</tt> and <tt>></tt> but you didn't want to allow +you wanted to support comparison operators like <tt><</tt> and <tt>></tt> but you didn't want to allow combinations like <tt>a < b < c</tt>. To do this, simply specify a rule like this: <blockquote> @@ -910,6 +1938,10 @@ precedence = ( </blockquote> <p> +If you do this, the occurrence of input text such as <tt> a < b < c</tt> will result in a syntax error. However, simple +expressions such as <tt>a < b</tt> will still be fine. + +<p> Reduce/reduce conflicts are caused when there are multiple grammar rules that can be applied to a given set of symbols. This kind of conflict is almost always bad and is always resolved by picking the @@ -941,11 +1973,17 @@ expression : NUMBER </blockquote> For example, if you wrote "a = 5", the parser can't figure out if this -is supposed to reduced as <tt>assignment : ID EQUALS NUMBER</tt> or +is supposed to be reduced as <tt>assignment : ID EQUALS NUMBER</tt> or whether it's supposed to reduce the 5 as an expression and then reduce the rule <tt>assignment : ID EQUALS expression</tt>. -<h2>The parser.out file</h2> +<p> +It should be noted that reduce/reduce conflicts are notoriously difficult to spot +simply looking at the input grammer. To locate these, it is usually easier to look at the +<tt>parser.out</tt> debugging file with an appropriately high level of caffeination. + +<H3><a name="ply_nn28"></a>5.7 The parser.out file</H3> + Tracking down shift/reduce and reduce/reduce conflicts is one of the finer pleasures of using an LR parsing algorithm. To assist in debugging, <tt>yacc.py</tt> creates a debugging file called @@ -981,7 +2019,7 @@ Nonterminals, with rules where they appear expression : 1 1 2 2 3 3 4 4 6 0 -Parsing method: SLR +Parsing method: LALR state 0 @@ -1220,7 +2258,8 @@ By looking at these rules (and with a little practice), you can usually track do of most parsing conflicts. It should also be stressed that not all shift-reduce conflicts are bad. However, the only way to be sure that they are resolved correctly is to look at <tt>parser.out</tt>. -<h2>Syntax Error Handling</h2> +<H3><a name="ply_nn29"></a>5.8 Syntax Error Handling</H3> + When a syntax error occurs during parsing, the error is immediately detected (i.e., the parser does not read any more tokens beyond the @@ -1259,14 +2298,15 @@ shifted onto the parsing stack. parser can successfully shift a new symbol or reduce a rule involving <tt>error</tt>. </ol> -<h4>Recovery and resynchronization with error rules</h4> +<H4><a name="ply_nn30"></a>5.8.1 Recovery and resynchronization with error rules</H4> + The most well-behaved approach for handling syntax errors is to write grammar rules that include the <tt>error</tt> token. For example, suppose your language had a grammar rule for a print statement like this: <blockquote> <pre> -def p_statement_print(t): +def p_statement_print(p): 'statement : PRINT expr SEMI' ... </pre> @@ -1276,7 +2316,7 @@ To account for the possibility of a bad expression, you might write an additiona <blockquote> <pre> -def p_statement_print_error(t): +def p_statement_print_error(p): 'statement : PRINT error SEMI' print "Syntax error in print statement. Bad expression" @@ -1300,7 +2340,7 @@ on the right in an error rule. For example: <blockquote> <pre> -def p_statement_print_error(t): +def p_statement_print_error(p): 'statement : PRINT error' print "Syntax error in print statement. Bad expression" </pre> @@ -1310,7 +2350,8 @@ This is because the first bad token encountered will cause the rule to be reduced--which may make it difficult to recover if more bad tokens immediately follow. -<h4>Panic mode recovery</h4> +<H4><a name="ply_nn31"></a>5.8.2 Panic mode recovery</H4> + An alternative error recovery scheme is to enter a panic mode recovery in which tokens are discarded to a point where the parser might be able to recover in some sensible manner. @@ -1322,7 +2363,7 @@ parser in its initial state. <blockquote> <pre> -def p_error(t): +def p_error(p): print "Whoa. You are seriously hosed." # Read ahead looking for a closing '}' while 1: @@ -1337,8 +2378,8 @@ This function simply discards the bad token and tells the parser that the error <blockquote> <pre> -def p_error(t): - print "Syntax error at token", t.type +def p_error(p): + print "Syntax error at token", p.type # Just discard the token and tell the parser it's okay. yacc.errok() </pre> @@ -1370,7 +2411,7 @@ useful if trying to synchronize on special characters. For example: <blockquote> <pre> -def p_error(t): +def p_error(p): # Read ahead looking for a terminating ";" while 1: tok = yacc.token() # Get the next token @@ -1382,47 +2423,110 @@ def p_error(t): </pre> </blockquote> -<h4>General comments on error handling</h4> +<H4><a name="ply_nn32"></a>5.8.3 General comments on error handling</H4> + For normal types of languages, error recovery with error rules and resynchronization characters is probably the most reliable technique. This is because you can instrument the grammar to catch errors at selected places where it is relatively easy to recover and continue parsing. Panic mode recovery is really only useful in certain specialized applications where you might want to discard huge portions of the input text to find a valid restart point. -<h2>Line Number Tracking</h2> +<H3><a name="ply_nn33"></a>5.9 Line Number and Position Tracking</H3> -<tt>yacc.py</tt> automatically tracks line numbers for all of the grammar symbols and tokens it processes. To retrieve the line -numbers, two functions are used in grammar rules: +Position tracking is often a tricky problem when writing compilers. By default, PLY tracks the line number and position of +all tokens. This information is available using the following functions: <ul> -<li><tt>t.lineno(num)</tt>. Return the starting line number for symbol <em>num</em> -<li><tt>t.linespan(num)</tt>. Return a tuple (startline,endline) with the starting and ending line number for symbol <em>num</em>. +<li><tt>p.lineno(num)</tt>. Return the line number for symbol <em>num</em> +<li><tt>p.lexpos(num)</tt>. Return the lexing position for symbol <em>num</em> </ul> For example: <blockquote> <pre> -def t_expression(t): +def p_expression(p): 'expression : expression PLUS expression' - t.lineno(1) # Line number of the left expression - t.lineno(2) # line number of the PLUS operator - t.lineno(3) # line number of the right expression + line = p.lineno(2) # line number of the PLUS token + index = p.lexpos(2) # Position of the PLUS token +</pre> +</blockquote> + +As an optional feature, <tt>yacc.py</tt> can automatically track line numbers and positions for all of the grammar symbols +as well. However, this +extra tracking requires extra processing and can significantly slow down parsing. Therefore, it must be enabled by passing the +<tt>tracking=True</tt> option to <tt>yacc.parse()</tt>. For example: + +<blockquote> +<pre> +yacc.parse(data,tracking=True) +</pre> +</blockquote> + +Once enabled, the <tt>lineno()</tt> and <tt>lexpos()</tt> methods work for all grammar symbols. In addition, two +additional methods can be used: + +<ul> +<li><tt>p.linespan(num)</tt>. Return a tuple (startline,endline) with the starting and ending line number for symbol <em>num</em>. +<li><tt>p.lexspan(num)</tt>. Return a tuple (start,end) with the starting and ending positions for symbol <em>num</em>. +</ul> + +For example: + +<blockquote> +<pre> +def p_expression(p): + 'expression : expression PLUS expression' + p.lineno(1) # Line number of the left expression + p.lineno(2) # line number of the PLUS operator + p.lineno(3) # line number of the right expression ... - start,end = t.linespan(3) # Start,end lines of the right expression + start,end = p.linespan(3) # Start,end lines of the right expression + starti,endi = p.lexspan(3) # Start,end positions of right expression + +</pre> +</blockquote> +Note: The <tt>lexspan()</tt> function only returns the range of values up to the start of the last grammar symbol. + +<p> +Although it may be convenient for PLY to track position information on +all grammar symbols, this is often unnecessary. For example, if you +are merely using line number information in an error message, you can +often just key off of a specific token in the grammar rule. For +example: + +<blockquote> +<pre> +def p_bad_func(p): + 'funccall : fname LPAREN error RPAREN' + # Line number reported from LPAREN token + print "Bad function call at line", p.lineno(2) </pre> </blockquote> -Since line numbers are managed internally by the parser, there is usually no need to modify the line -numbers. However, if you want to save the line numbers in a parse-tree node, you will need to make your own -private copy. +<p> +Similarly, you may get better parsing performance if you only propagate line number +information where it's needed. For example: + +<blockquote> +<pre> +def p_fname(p): + 'fname : ID' + p[0] = (p[1],p.lineno(1)) +</pre> +</blockquote> + +Finally, it should be noted that PLY does not store position information after a rule has been +processed. If it is important for you to retain this information in an abstract syntax tree, you +must make your own copy. + +<H3><a name="ply_nn34"></a>5.10 AST Construction</H3> -<h2>AST Construction</h2> <tt>yacc.py</tt> provides no special functions for constructing an abstract syntax tree. However, such construction is easy enough to do on your own. Simply create a data structure for abstract syntax tree nodes -and assign nodes to <tt>t[0]</tt> in each rule. +and assign nodes to <tt>p[0]</tt> in each rule. For example: @@ -1442,21 +2546,21 @@ class Number(Expr): self.type = "number" self.value = value -def p_expression_binop(t): +def p_expression_binop(p): '''expression : expression PLUS expression | expression MINUS expression | expression TIMES expression | expression DIVIDE expression''' - t[0] = BinOp(t[1],t[2],t[3]) + p[0] = BinOp(p[1],p[2],p[3]) -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] = Number(t[1]) + p[0] = Number(p[1]) </pre> </blockquote> @@ -1474,19 +2578,144 @@ class Node: self.children = [ ] self.leaf = leaf -def p_expression_binop(t): +def p_expression_binop(p): '''expression : expression PLUS expression | expression MINUS expression | expression TIMES expression | expression DIVIDE expression''' - t[0] = Node("binop", [t[1],t[3]], t[2]) + p[0] = Node("binop", [p[1],p[3]], p[2]) +</pre> +</blockquote> + +<H3><a name="ply_nn35"></a>5.11 Embedded Actions</H3> + + +The parsing technique used by yacc only allows actions to be executed at the end of a rule. For example, +suppose you have a rule like this: + +<blockquote> +<pre> +def p_foo(p): + "foo : A B C D" + print "Parsed a foo", p[1],p[2],p[3],p[4] +</pre> +</blockquote> + +<p> +In this case, the supplied action code only executes after all of the +symbols <tt>A</tt>, <tt>B</tt>, <tt>C</tt>, and <tt>D</tt> have been +parsed. Sometimes, however, it is useful to execute small code +fragments during intermediate stages of parsing. For example, suppose +you wanted to perform some action immediately after <tt>A</tt> has +been parsed. To do this, you can write a empty rule like this: + +<blockquote> +<pre> +def p_foo(p): + "foo : A seen_A B C D" + print "Parsed a foo", p[1],p[3],p[4],p[5] + print "seen_A returned", p[2] + +def p_seen_A(p): + "seen_A :" + print "Saw an A = ", p[-1] # Access grammar symbol to left + p[0] = some_value # Assign value to seen_A + +</pre> +</blockquote> + +<p> +In this example, the empty <tt>seen_A</tt> rule executes immediately +after <tt>A</tt> is shifted onto the parsing stack. Within this +rule, <tt>p[-1]</tt> refers to the symbol on the stack that appears +immediately to the left of the <tt>seen_A</tt> symbol. In this case, +it would be the value of <tt>A</tt> in the <tt>foo</tt> rule +immediately above. Like other rules, a value can be returned from an +embedded action by simply assigning it to <tt>p[0]</tt> + +<p> +The use of embedded actions can sometimes introduce extra shift/reduce conflicts. For example, +this grammar has no conflicts: + +<blockquote> +<pre> +def p_foo(p): + """foo : abcd + | abcx""" + +def p_abcd(p): + "abcd : A B C D" + +def p_abcx(p): + "abcx : A B C X" +</pre> +</blockquote> + +However, if you insert an embedded action into one of the rules like this, + +<blockquote> +<pre> +def p_foo(p): + """foo : abcd + | abcx""" + +def p_abcd(p): + "abcd : A B C D" + +def p_abcx(p): + "abcx : A B seen_AB C X" + +def p_seen_AB(p): + "seen_AB :" +</pre> +</blockquote> + +an extra shift-reduce conflict will be introduced. This conflict is caused by the fact that the same symbol <tt>C</tt> appears next in +both the <tt>abcd</tt> and <tt>abcx</tt> rules. The parser can either shift the symbol (<tt>abcd</tt> rule) or reduce the empty rule <tt>seen_AB</tt> (<tt>abcx</tt> rule). + +<p> +A common use of embedded rules is to control other aspects of parsing +such as scoping of local variables. For example, if you were parsing C code, you might +write code like this: + +<blockquote> +<pre> +def p_statements_block(p): + "statements: LBRACE new_scope statements RBRACE""" + # Action code + ... + pop_scope() # Return to previous scope + +def p_new_scope(p): + "new_scope :" + # Create a new scope for local variables + s = new_scope() + push_scope(s) + ... </pre> </blockquote> -<h2>Yacc implementation notes</h2> +In this case, the embedded action <tt>new_scope</tt> executes immediately after a <tt>LBRACE</tt> (<tt>{</tt>) symbol is parsed. This might +adjust internal symbol tables and other aspects of the parser. Upon completion of the rule <tt>statements_block</tt>, code might undo the operations performed in the embedded action (e.g., <tt>pop_scope()</tt>). + +<H3><a name="ply_nn36"></a>5.12 Yacc implementation notes</H3> + <ul> +<li>The default parsing method is LALR. To use SLR instead, run yacc() as follows: + +<blockquote> +<pre> +yacc.yacc(method="SLR") +</pre> +</blockquote> +Note: LALR table generation takes approximately twice as long as SLR table generation. There is no +difference in actual parsing performance---the same code is used in both cases. LALR is preferred when working +with more complicated grammars since it is more powerful. + +<p> + <li>By default, <tt>yacc.py</tt> relies on <tt>lex.py</tt> for tokenizing. However, an alternative tokenizer can be supplied as follows: @@ -1517,6 +2746,25 @@ yacc.yacc(tabmodule="foo") </pre> </blockquote> +<p> +<li>To change the directory in which the <tt>parsetab.py</tt> file (and other output files) are written, use: +<blockquote> +<pre> +yacc.yacc(tabmodule="foo",outputdir="somedirectory") +</pre> +</blockquote> + +<p> +<li>To prevent yacc from generating any kind of parser table file, use: +<blockquote> +<pre> +yacc.yacc(write_tables=0) +</pre> +</blockquote> + +Note: If you disable table generation, yacc() will regenerate the parsing tables +each time it runs (which may take awhile depending on how large your grammar is). + <P> <li>To print copious amounts of debugging during parsing, use: @@ -1527,6 +2775,15 @@ yacc.parse(debug=1) </blockquote> <p> +<li>To redirect the debugging output to a filename of your choosing, use: + +<blockquote> +<pre> +yacc.parse(debug=1, debugfile="debugging.out") +</pre> +</blockquote> + +<p> <li>The <tt>yacc.yacc()</tt> function really returns a parser object. If you want to support multiple parsers in the same application, do this: @@ -1541,7 +2798,7 @@ p.parse() Note: The function <tt>yacc.parse()</tt> is bound to the last parser that was generated. <p> -<li>Since the generation of the SLR tables is relatively expensive, previously generated tables are +<li>Since the generation of the LALR tables is relatively expensive, previously generated tables are cached and reused if possible. The decision to regenerate the tables is determined by taking an MD5 checksum of all grammar rules and precedence rules. Only in the event of a mismatch are the tables regenerated. @@ -1551,11 +2808,12 @@ and several hundred states. For more complex languages such as C, table generat machine. Please be patient. <p> -<li>Since LR parsing is mostly driven by tables, the performance of the parser is largely independent of the -size of the grammar. The biggest bottlenecks will be the lexer and the complexity of your grammar rules. +<li>Since LR parsing is driven by tables, the performance of the parser is largely independent of the +size of the grammar. The biggest bottlenecks will be the lexer and the complexity of the code in your grammar rules. </ul> -<h2>Parser and Lexer State Management</h2> +<H2><a name="ply_nn37"></a>6. Parser and Lexer State Management</H2> + In advanced parsing applications, you may want to have multiple parsers and lexers. Furthermore, the parser may want to control the @@ -1573,6 +2831,14 @@ parser = yacc.yacc() # Return parser object </pre> </blockquote> +To attach the lexer and parser together, make sure you use the <tt>lexer</tt> argumemnt to parse. For example: + +<blockquote> +<pre> +parser.parse(text,lexer=lexer) +</pre> +</blockquote> + Within lexer and parser rules, these objects are also available. In the lexer, the "lexer" attribute of a token refers to the lexer object in use. For example: @@ -1590,11 +2856,11 @@ and parser objects respectively. <blockquote> <pre> -def p_expr_plus(t): +def p_expr_plus(p): 'expr : expr PLUS expr' ... - print t.parser # Show parser object - print t.lexer # Show lexer object + print p.parser # Show parser object + print p.lexer # Show lexer object </pre> </blockquote> @@ -1602,7 +2868,8 @@ If necessary, arbitrary attributes can be attached to the lexer or parser object For example, if you wanted to have different parsing modes, you could attach a mode attribute to the parser object and look at it later. -<h2>Using Python's Optimized Mode</h2> +<H2><a name="ply_nn38"></a>7. Using Python's Optimized Mode</H2> + Because PLY uses information from doc-strings, parsing and lexing information must be gathered while running the Python interpreter in @@ -1626,7 +2893,8 @@ Beware: running PLY in optimized mode disables a lot of error checking. You should only do this when your project has stabilized and you don't need to do any debugging. -<h2>Where to go from here?</h2> +<H2><a name="ply_nn39"></a>8. Where to go from here?</H2> + The <tt>examples</tt> directory of the PLY distribution contains several simple examples. Please consult a compilers textbook for the theory and underlying implementation details or LR parsing. diff --git a/ext/ply/example/BASIC/README b/ext/ply/example/BASIC/README new file mode 100644 index 000000000..be24a3005 --- /dev/null +++ b/ext/ply/example/BASIC/README @@ -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 + + + + + + diff --git a/ext/ply/example/BASIC/basic.py b/ext/ply/example/BASIC/basic.py new file mode 100644 index 000000000..3a07acdbf --- /dev/null +++ b/ext/ply/example/BASIC/basic.py @@ -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() + + + + + + + + + diff --git a/ext/ply/example/BASIC/basiclex.py b/ext/ply/example/BASIC/basiclex.py new file mode 100644 index 000000000..727383f2b --- /dev/null +++ b/ext/ply/example/BASIC/basiclex.py @@ -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() + + + + + + + + + + + + + + + + + diff --git a/ext/ply/example/BASIC/basinterp.py b/ext/ply/example/BASIC/basinterp.py new file mode 100644 index 000000000..5850457cb --- /dev/null +++ b/ext/ply/example/BASIC/basinterp.py @@ -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 + diff --git a/ext/ply/example/BASIC/basparse.py b/ext/ply/example/BASIC/basparse.py new file mode 100644 index 000000000..930af9a22 --- /dev/null +++ b/ext/ply/example/BASIC/basparse.py @@ -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 + + + + + + + + + + + + + + diff --git a/ext/ply/example/BASIC/dim.bas b/ext/ply/example/BASIC/dim.bas new file mode 100644 index 000000000..87bd95b32 --- /dev/null +++ b/ext/ply/example/BASIC/dim.bas @@ -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 diff --git a/ext/ply/example/BASIC/func.bas b/ext/ply/example/BASIC/func.bas new file mode 100644 index 000000000..447ee16a9 --- /dev/null +++ b/ext/ply/example/BASIC/func.bas @@ -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 diff --git a/ext/ply/example/BASIC/gcd.bas b/ext/ply/example/BASIC/gcd.bas new file mode 100644 index 000000000..d0b774608 --- /dev/null +++ b/ext/ply/example/BASIC/gcd.bas @@ -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 diff --git a/ext/ply/example/BASIC/gosub.bas b/ext/ply/example/BASIC/gosub.bas new file mode 100644 index 000000000..99737b16f --- /dev/null +++ b/ext/ply/example/BASIC/gosub.bas @@ -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 diff --git a/ext/ply/example/BASIC/hello.bas b/ext/ply/example/BASIC/hello.bas new file mode 100644 index 000000000..cc6f0b0b5 --- /dev/null +++ b/ext/ply/example/BASIC/hello.bas @@ -0,0 +1,4 @@ +5 REM HELLO WORLD PROGAM +10 PRINT "HELLO WORLD" +99 END + diff --git a/ext/ply/example/BASIC/linear.bas b/ext/ply/example/BASIC/linear.bas new file mode 100644 index 000000000..56c08220b --- /dev/null +++ b/ext/ply/example/BASIC/linear.bas @@ -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 diff --git a/ext/ply/example/BASIC/maxsin.bas b/ext/ply/example/BASIC/maxsin.bas new file mode 100644 index 000000000..b96901530 --- /dev/null +++ b/ext/ply/example/BASIC/maxsin.bas @@ -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 diff --git a/ext/ply/example/BASIC/powers.bas b/ext/ply/example/BASIC/powers.bas new file mode 100644 index 000000000..a454dc3e2 --- /dev/null +++ b/ext/ply/example/BASIC/powers.bas @@ -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 diff --git a/ext/ply/example/BASIC/rand.bas b/ext/ply/example/BASIC/rand.bas new file mode 100644 index 000000000..4ff7a1467 --- /dev/null +++ b/ext/ply/example/BASIC/rand.bas @@ -0,0 +1,4 @@ +10 FOR I = 1 TO 20 +20 PRINT INT(10*RND(0)) +30 NEXT I +40 END diff --git a/ext/ply/example/BASIC/sales.bas b/ext/ply/example/BASIC/sales.bas new file mode 100644 index 000000000..a39aefb76 --- /dev/null +++ b/ext/ply/example/BASIC/sales.bas @@ -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 diff --git a/ext/ply/example/BASIC/sears.bas b/ext/ply/example/BASIC/sears.bas new file mode 100644 index 000000000..5ced3974e --- /dev/null +++ b/ext/ply/example/BASIC/sears.bas @@ -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 diff --git a/ext/ply/example/BASIC/sqrt1.bas b/ext/ply/example/BASIC/sqrt1.bas new file mode 100644 index 000000000..6673a9152 --- /dev/null +++ b/ext/ply/example/BASIC/sqrt1.bas @@ -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 diff --git a/ext/ply/example/BASIC/sqrt2.bas b/ext/ply/example/BASIC/sqrt2.bas new file mode 100644 index 000000000..862d85ef2 --- /dev/null +++ b/ext/ply/example/BASIC/sqrt2.bas @@ -0,0 +1,4 @@ +10 FOR X = 1 TO 100 +20 PRINT X, SQR(X) +30 NEXT X +40 END diff --git a/ext/ply/example/GardenSnake/GardenSnake.py b/ext/ply/example/GardenSnake/GardenSnake.py new file mode 100644 index 000000000..ffa550fc6 --- /dev/null +++ b/ext/ply/example/GardenSnake/GardenSnake.py @@ -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" diff --git a/ext/ply/example/GardenSnake/README b/ext/ply/example/GardenSnake/README new file mode 100644 index 000000000..4d8be2db0 --- /dev/null +++ b/ext/ply/example/GardenSnake/README @@ -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 + diff --git a/ext/ply/example/README b/ext/ply/example/README new file mode 100644 index 000000000..63519b557 --- /dev/null +++ b/ext/ply/example/README @@ -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. + diff --git a/ext/ply/example/ansic/clex.py b/ext/ply/example/ansic/clex.py index afd995208..12441a60b 100644 --- a/ext/ply/example/ansic/clex.py +++ b/ext/ply/example/ansic/clex.py @@ -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__": diff --git a/ext/ply/example/ansic/cparse.py b/ext/ply/example/ansic/cparse.py index ddfd5c72b..d474378c8 100644 --- a/ext/ply/example/ansic/cparse.py +++ b/ext/ply/example/ansic/cparse.py @@ -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')") diff --git a/ext/ply/example/calc/calc.py b/ext/ply/example/calc/calc.py index aeb23c246..987ce8019 100644 --- a/ext/ply/example/calc/calc.py +++ b/ext/ply/example/calc/calc.py @@ -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] - -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_uminus(t): - 'expression : MINUS expression %prec UMINUS' - t[0] = -t[2] - -def p_expression_group(t): - 'expression : LPAREN expression RPAREN' - t[0] = t[2] - -def p_expression_number(t): - 'expression : NUMBER' - t[0] = t[1] - -def p_expression_name(t): - 'expression : NAME' + print p[1] + +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(p): + "expression : '-' expression %prec UMINUS" + p[0] = -p[2] + +def p_expression_group(p): + "expression : '(' expression ')'" + p[0] = p[2] + +def p_expression_number(p): + "expression : NUMBER" + p[0] = p[1] + +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) diff --git a/ext/ply/example/classcalc/calc.py b/ext/ply/example/classcalc/calc.py new file mode 100644 index 000000000..b2f3f70f1 --- /dev/null +++ b/ext/ply/example/classcalc/calc.py @@ -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() diff --git a/ext/ply/example/cleanup.sh b/ext/ply/example/cleanup.sh new file mode 100644 index 000000000..3e115f41c --- /dev/null +++ b/ext/ply/example/cleanup.sh @@ -0,0 +1,2 @@ +#!/bin/sh +rm -f */*.pyc */parsetab.py */parser.out */*~ */*.class diff --git a/ext/ply/example/hedit/hedit.py b/ext/ply/example/hedit/hedit.py index f00427bf5..494f4fde5 100644 --- a/ext/ply/example/hedit/hedit.py +++ b/ext/ply/example/hedit/hedit.py @@ -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() diff --git a/ext/ply/example/newclasscalc/calc.py b/ext/ply/example/newclasscalc/calc.py new file mode 100644 index 000000000..7f29bc821 --- /dev/null +++ b/ext/ply/example/newclasscalc/calc.py @@ -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() diff --git a/ext/ply/example/optcalc/calc.py b/ext/ply/example/optcalc/calc.py index fa66cda5b..3a0ee6c9b 100644 --- a/ext/ply/example/optcalc/calc.py +++ b/ext/ply/example/optcalc/calc.py @@ -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: diff --git a/ext/ply/example/unicalc/calc.py b/ext/ply/example/unicalc/calc.py new file mode 100644 index 000000000..d1f59f748 --- /dev/null +++ b/ext/ply/example/unicalc/calc.py @@ -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)) diff --git a/ext/ply/example/yply/README b/ext/ply/example/yply/README new file mode 100644 index 000000000..bfadf3643 --- /dev/null +++ b/ext/ply/example/yply/README @@ -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 + diff --git a/ext/ply/example/yply/ylex.py b/ext/ply/example/yply/ylex.py new file mode 100644 index 000000000..61bc0c7ef --- /dev/null +++ b/ext/ply/example/yply/ylex.py @@ -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() + + + + + + + diff --git a/ext/ply/example/yply/yparse.py b/ext/ply/example/yply/yparse.py new file mode 100644 index 000000000..a4e46bef7 --- /dev/null +++ b/ext/ply/example/yply/yparse.py @@ -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) + diff --git a/ext/ply/example/yply/yply.py b/ext/ply/example/yply/yply.py new file mode 100644 index 000000000..a4398171e --- /dev/null +++ b/ext/ply/example/yply/yply.py @@ -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() +""" + + diff --git a/ext/ply/lex.py b/ext/ply/lex.py deleted file mode 100644 index 7ad7a394b..000000000 --- a/ext/ply/lex.py +++ /dev/null @@ -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) - - - - diff --git a/ext/ply/ply/__init__.py b/ext/ply/ply/__init__.py new file mode 100644 index 000000000..853a98554 --- /dev/null +++ b/ext/ply/ply/__init__.py @@ -0,0 +1,4 @@ +# PLY package +# Author: David Beazley (dave@dabeaz.com) + +__all__ = ['lex','yacc'] diff --git a/ext/ply/ply/lex.py b/ext/ply/ply/lex.py new file mode 100644 index 000000000..782b29286 --- /dev/null +++ b/ext/ply/ply/lex.py @@ -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 + diff --git a/ext/ply/yacc.py b/ext/ply/ply/yacc.py index 1041745ed..39c17a9ed 100644 --- a/ext/ply/yacc.py +++ b/ext/ply/ply/yacc.py @@ -1,14 +1,9 @@ #----------------------------------------------------------------------------- # ply: yacc.py # -# Author: David M. Beazley (beazley@cs.uchicago.edu) -# Department of Computer Science -# University of Chicago -# Chicago, IL 60637 +# Author(s): David M. Beazley (dave@dabeaz.com) # -# Copyright (C) 2001, David M. Beazley -# -# $Header: /home/stever/bk/newmem2/ext/ply/yacc.py 1.3 03/06/06 14:59:28-00:00 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 @@ -28,12 +23,10 @@ # # # This implements an LR parser that is constructed from grammar rules defined -# as Python functions. Roughly speaking, this module is a cross between -# John Aycock's Spark system and the GNU bison utility. -# -# Disclaimer: This is a work in progress. SLR parsing seems to work fairly -# well and there is extensive error checking. LALR(1) is in progress. The -# rest of this file is a bit of a mess. Please pardon the dust. +# as Python functions. The grammer is specified by supplying the BNF inside +# Python documentation strings. The inspiration for this technique was borrowed +# from John Aycock's Spark parsing system. PLY might be viewed as cross between +# Spark and the GNU bison utility. # # The current implementation is only somewhat object-oriented. The # LR parser itself is defined in terms of an object (which allows multiple @@ -41,9 +34,23 @@ # construction are defined in terms of global variables. Users shouldn't # notice unless they are trying to define multiple parsers at the same # time using threads (in which case they should have their head examined). -#----------------------------------------------------------------------------- +# +# This implementation supports both SLR and LALR(1) parsing. LALR(1) +# support was originally implemented by Elias Ioup (ezioup@alumni.uchicago.edu), +# using the algorithm found in Aho, Sethi, and Ullman "Compilers: Principles, +# Techniques, and Tools" (The Dragon Book). LALR(1) has since been replaced +# by the more efficient DeRemer and Pennello algorithm. +# +# :::::::: WARNING ::::::: +# +# Construction of LR parsing tables is fairly complicated and expensive. +# To make this module run fast, a *LOT* of work has been put into +# optimization---often at the expensive of readability and what might +# consider to be good Python "coding style." Modify the code at your +# own risk! +# ---------------------------------------------------------------------------- -__version__ = "1.3" +__version__ = "2.3" #----------------------------------------------------------------------------- # === User configurable parameters === @@ -56,7 +63,7 @@ yaccdebug = 1 # Debugging mode. If set, yacc generates a debug_file = 'parser.out' # Default name of the debugging file tab_module = 'parsetab' # Default name of the table module -default_lr = 'SLR' # Default LR table generation method +default_lr = 'LALR' # Default LR table generation method error_count = 3 # Number of symbols that must be shifted to leave recovery mode @@ -65,6 +72,16 @@ import re, types, sys, cStringIO, md5, os.path # Exception raised for yacc-related errors class YaccError(Exception): pass +# Available instance types. This is used when parsers 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 + #----------------------------------------------------------------------------- # === LR Parsing Engine === # @@ -79,8 +96,10 @@ class YaccError(Exception): pass # .value = Symbol value # .lineno = Starting line number # .endlineno = Ending line number (optional, set automatically) +# .lexpos = Starting lex position +# .endlexpos = Ending lex position (optional, set automatically) -class YaccSymbol: +class YaccSymbol(object): def __str__(self): return self.type def __repr__(self): return str(self) @@ -90,19 +109,24 @@ class YaccSymbol: # The lineno() method returns the line number of a given # item (or 0 if not defined). The linespan() method returns # a tuple of (startline,endline) representing the range of lines -# for a symbol. +# for a symbol. The lexspan() method returns a tuple (lexpos,endlexpos) +# representing the range of positional information for a symbol. -class YaccSlice: - def __init__(self,s): +class YaccProduction: + def __init__(self,s,stack=None): self.slice = s self.pbstack = [] - + self.stack = stack def __getitem__(self,n): - return self.slice[n].value + if n >= 0: return self.slice[n].value + else: return self.stack[n].value def __setitem__(self,n,v): self.slice[n].value = v + def __getslice__(self,i,j): + return [s.value for s in self.slice[i:j]] + def __len__(self): return len(self.slice) @@ -114,6 +138,14 @@ class YaccSlice: endline = getattr(self.slice[n],"endlineno",startline) return startline,endline + def lexpos(self,n): + return getattr(self.slice[n],"lexpos",0) + + def lexspan(self,n): + startpos = getattr(self.slice[n],"lexpos",0) + endpos = getattr(self.slice[n],"endlexpos",startpos) + return startpos,endpos + def pushback(self,n): if n <= 0: raise ValueError, "Expected a positive value" @@ -145,31 +177,32 @@ class Parser: self.method = "Unknown LR" # Table construction method used def errok(self): - self.errorcount = 0 + self.errorok = 1 def restart(self): del self.statestack[:] del self.symstack[:] sym = YaccSymbol() - sym.type = '$' + sym.type = '$end' self.symstack.append(sym) self.statestack.append(0) - def parse(self,input=None,lexer=None,debug=0): + def parse(self,input=None,lexer=None,debug=0,tracking=0): lookahead = None # Current lookahead symbol lookaheadstack = [ ] # Stack of lookahead symbols actions = self.action # Local reference to action table goto = self.goto # Local reference to goto table prod = self.productions # Local reference to production list - pslice = YaccSlice(None) # Slice object passed to grammar rules - pslice.parser = self # Parser object - self.errorcount = 0 # Used during error recovery + pslice = YaccProduction(None) # Production object passed to grammar rules + errorcount = 0 # Used during error recovery # If no lexer was given, we will try to use the lex module if not lexer: - import lex as lexer + import lex + lexer = lex.lexer pslice.lexer = lexer + pslice.parser = self # If input was supplied, pass to lexer if input: @@ -183,18 +216,22 @@ class Parser: symstack = [ ] # Stack of grammar symbols self.symstack = symstack + pslice.stack = symstack # Put in the production errtoken = None # Err token - # The start state is assumed to be (0,$) + # The start state is assumed to be (0,$end) + statestack.append(0) sym = YaccSymbol() - sym.type = '$' + sym.type = '$end' symstack.append(sym) - + state = 0 while 1: # Get the next symbol on the input. If a lookahead symbol # is already set, we just use that. Otherwise, we'll pull # the next token off of the lookaheadstack or from the lexer + if debug > 1: + print 'state', state if not lookahead: if not lookaheadstack: lookahead = get_token() # Get the next token @@ -202,30 +239,32 @@ class Parser: lookahead = lookaheadstack.pop() if not lookahead: lookahead = YaccSymbol() - lookahead.type = '$' + lookahead.type = '$end' if debug: - print "%-20s : %s" % (lookahead, [xx.type for xx in symstack]) + errorlead = ("%s . %s" % (" ".join([xx.type for xx in symstack][1:]), str(lookahead))).lstrip() # Check the action table - s = statestack[-1] ltype = lookahead.type - t = actions.get((s,ltype),None) + t = actions[state].get(ltype) + if debug > 1: + print 'action', t if t is not None: if t > 0: # shift a symbol on the stack - if ltype == '$': + if ltype == '$end': # Error, end of input - print "yacc: Parse error. EOF" + sys.stderr.write("yacc: Parse error. EOF\n") return statestack.append(t) + state = t + if debug > 1: + sys.stderr.write("%-60s shift state %s\n" % (errorlead, t)) symstack.append(lookahead) lookahead = None # Decrease error count on successful shift - if self.errorcount > 0: - self.errorcount -= 1 - + if errorcount: errorcount -=1 continue if t < 0: @@ -238,57 +277,42 @@ class Parser: sym = YaccSymbol() sym.type = pname # Production name sym.value = None + if debug > 1: + sys.stderr.write("%-60s reduce %d\n" % (errorlead, -t)) if plen: targ = symstack[-plen-1:] targ[0] = sym - try: - sym.lineno = targ[1].lineno - sym.endlineno = getattr(targ[-1],"endlineno",targ[-1].lineno) - except AttributeError: - sym.lineno = 0 + if tracking: + t1 = targ[1] + sym.lineno = t1.lineno + sym.lexpos = t1.lexpos + t1 = targ[-1] + sym.endlineno = getattr(t1,"endlineno",t1.lineno) + sym.endlexpos = getattr(t1,"endlexpos",t1.lexpos) del symstack[-plen:] del statestack[-plen:] else: - sym.lineno = 0 + if tracking: + sym.lineno = lexer.lineno + sym.lexpos = lexer.lexpos targ = [ sym ] pslice.slice = targ - pslice.pbstack = [] + # Call the grammar rule with our special slice object p.func(pslice) - # Validate attributes of the resulting value attribute -# if require: -# try: -# t0 = targ[0] -# r = Requires.get(t0.type,None) -# t0d = t0.__dict__ -# if r: -# for field in r: -# tn = t0 -# for fname in field: -# try: -# tf = tn.__dict__ -# tn = tf.get(fname) -# except StandardError: -# tn = None -# if not tn: -# print "%s:%d: Rule %s doesn't set required attribute '%s'" % \ -# (p.file,p.line,p.name,".".join(field)) -# except TypeError,LookupError: -# print "Bad requires directive " % r -# pass - - # If there was a pushback, put that on the stack if pslice.pbstack: lookaheadstack.append(lookahead) for _t in pslice.pbstack: lookaheadstack.append(_t) lookahead = None + pslice.pbstack = [] symstack.append(sym) - statestack.append(goto[statestack[-1],pname]) + state = goto[statestack[-1]][pname] + statestack.append(state) continue if t == 0: @@ -296,19 +320,23 @@ class Parser: return getattr(n,"value",None) if t == None: - # We have some kind of parsing error here. To handle this, - # we are going to push the current token onto the tokenstack - # and replace it with an 'error' token. If there are any synchronization - # rules, they may catch it. + if debug: + sys.stderr.write(errorlead + "\n") + # We have some kind of parsing error here. To handle + # this, we are going to push the current token onto + # the tokenstack and replace it with an 'error' token. + # If there are any synchronization rules, they may + # catch it. # - # In addition to pushing the error token, we call call the user defined p_error() - # function if this is the first syntax error. This function is only called - # if errorcount == 0. - - if not self.errorcount: - self.errorcount = error_count + # In addition to pushing the error token, we call call + # the user defined p_error() function if this is the + # first syntax error. This function is only called if + # errorcount == 0. + if errorcount == 0 or self.errorok: + errorcount = error_count + self.errorok = 0 errtoken = lookahead - if errtoken.type == '$': + if errtoken.type == '$end': errtoken = None # End of file! if self.errorfunc: global errok,token,restart @@ -318,9 +346,10 @@ class Parser: tok = self.errorfunc(errtoken) del errok, token, restart # Delete special functions - if not self.errorcount: - # User must have done some kind of panic mode recovery on their own. The returned token - # is the next lookahead + if self.errorok: + # User must have done some kind of panic + # mode recovery on their own. The + # returned token is the next lookahead lookahead = tok errtoken = None continue @@ -329,21 +358,21 @@ class Parser: if hasattr(errtoken,"lineno"): lineno = lookahead.lineno else: lineno = 0 if lineno: - print "yacc: Syntax error at line %d, token=%s" % (lineno, errtoken.type) + sys.stderr.write("yacc: Syntax error at line %d, token=%s\n" % (lineno, errtoken.type)) else: - print "yacc: Syntax error, token=%s" % errtoken.type + sys.stderr.write("yacc: Syntax error, token=%s" % errtoken.type) else: - print "yacc: Parse error in input. EOF" + sys.stderr.write("yacc: Parse error in input. EOF\n") return else: - self.errorcount = error_count + errorcount = error_count # case 1: the statestack only has 1 entry on it. If we're in this state, the # entire parse has been rolled back and we're completely hosed. The token is # discarded and we just keep going. - if len(statestack) <= 1 and lookahead.type != '$': + if len(statestack) <= 1 and lookahead.type != '$end': lookahead = None errtoken = None # Nuke the pushback stack @@ -354,7 +383,7 @@ class Parser: # at the end of the file. nuke the top entry and generate an error token # Start nuking entries on the stack - if lookahead.type == '$': + if lookahead.type == '$end': # Whoa. We're really hosed here. Bail out return @@ -427,7 +456,7 @@ def validate_file(filename): if not prev: counthash[name] = linen else: - print "%s:%d: Function %s redefined. Previously defined on line %d" % (filename,linen,name,prev) + sys.stderr.write("%s:%d: Function %s redefined. Previously defined on line %d\n" % (filename,linen,name,prev)) noerror = 0 linen += 1 return noerror @@ -435,16 +464,16 @@ def validate_file(filename): # This function looks for functions that might be grammar rules, but which don't have the proper p_suffix. def validate_dict(d): for n,v in d.items(): - if n[0:2] == 'p_' and isinstance(v,types.FunctionType): continue + if n[0:2] == 'p_' and type(v) in (types.FunctionType, types.MethodType): continue if n[0:2] == 't_': continue if n[0:2] == 'p_': - print "yacc: Warning. '%s' not defined as a function" % n - if isinstance(v,types.FunctionType) and v.func_code.co_argcount == 1: + sys.stderr.write("yacc: Warning. '%s' not defined as a function\n" % n) + if 1 and isinstance(v,types.FunctionType) and v.func_code.co_argcount == 1: try: doc = v.__doc__.split(" ") if doc[1] == ':': - print "%s:%d: Warning. Possible grammar rule '%s' defined without p_ prefix." % (v.func_code.co_filename, v.func_code.co_firstlineno,n) + sys.stderr.write("%s:%d: Warning. Possible grammar rule '%s' defined without p_ prefix.\n" % (v.func_code.co_filename, v.func_code.co_firstlineno,n)) except StandardError: pass @@ -520,6 +549,7 @@ def initialize_vars(): # lr_next - Next LR item. Example, if we are ' E -> E . PLUS E' # then lr_next refers to 'E -> E PLUS . E' # lr_index - LR item index (location of the ".") in the prod list. +# lookaheads - LALR lookahead symbols for this item # len - Length of the production (number of symbols on right hand side) # ----------------------------------------------------------------------------- @@ -529,7 +559,11 @@ class Production: setattr(self,k,v) self.lr_index = -1 self.lr0_added = 0 # Flag indicating whether or not added to LR0 closure + self.lr1_added = 0 # Flag indicating whether or not added to LR1 self.usyms = [ ] + self.lookaheads = { } + self.lk_added = { } + self.setnumbers = [ ] def __str__(self): if self.prod: @@ -549,6 +583,8 @@ class Production: p.prod = list(self.prod) p.number = self.number p.lr_index = n + p.lookaheads = { } + p.setnumbers = self.setnumbers p.prod.insert(n,".") p.prod = tuple(p.prod) p.len = len(p.prod) @@ -569,11 +605,8 @@ class Production: class MiniProduction: pass -# Utility function -def is_identifier(s): - for c in s: - if not (c.isalnum() or c == '_'): return 0 - return 1 +# regex matching identifiers +_is_identifier = re.compile(r'^[a-zA-Z0-9_-]+$') # ----------------------------------------------------------------------------- # add_production() @@ -595,27 +628,40 @@ def is_identifier(s): def add_production(f,file,line,prodname,syms): if Terminals.has_key(prodname): - print "%s:%d: Illegal rule name '%s'. Already defined as a token." % (file,line,prodname) + sys.stderr.write("%s:%d: Illegal rule name '%s'. Already defined as a token.\n" % (file,line,prodname)) return -1 if prodname == 'error': - print "%s:%d: Illegal rule name '%s'. error is a reserved word." % (file,line,prodname) + sys.stderr.write("%s:%d: Illegal rule name '%s'. error is a reserved word.\n" % (file,line,prodname)) return -1 - if not is_identifier(prodname): - print "%s:%d: Illegal rule name '%s'" % (file,line,prodname) + if not _is_identifier.match(prodname): + sys.stderr.write("%s:%d: Illegal rule name '%s'\n" % (file,line,prodname)) return -1 - for s in syms: - if not is_identifier(s) and s != '%prec': - print "%s:%d: Illegal name '%s' in rule '%s'" % (file,line,s, prodname) + for x in range(len(syms)): + s = syms[x] + if s[0] in "'\"": + try: + c = eval(s) + if (len(c) > 1): + sys.stderr.write("%s:%d: Literal token %s in rule '%s' may only be a single character\n" % (file,line,s, prodname)) + return -1 + if not Terminals.has_key(c): + Terminals[c] = [] + syms[x] = c + continue + except SyntaxError: + pass + if not _is_identifier.match(s) and s != '%prec': + sys.stderr.write("%s:%d: Illegal name '%s' in rule '%s'\n" % (file,line,s, prodname)) return -1 # See if the rule is already in the rulemap map = "%s -> %s" % (prodname,syms) if Prodmap.has_key(map): m = Prodmap[map] - print "%s:%d: Duplicate rule %s." % (file,line, m) - print "%s:%d: Previous definition at %s:%d" % (file,line, m.file, m.line) + sys.stderr.write("%s:%d: Duplicate rule %s.\n" % (file,line, m)) + sys.stderr.write("%s:%d: Previous definition at %s:%d\n" % (file,line, m.file, m.line)) return -1 p = Production() @@ -640,12 +686,12 @@ def add_production(f,file,line,prodname,syms): try: precname = p.prod[i+1] except IndexError: - print "%s:%d: Syntax error. Nothing follows %%prec." % (p.file,p.line) + sys.stderr.write("%s:%d: Syntax error. Nothing follows %%prec.\n" % (p.file,p.line)) return -1 prec = Precedence.get(precname,None) if not prec: - print "%s:%d: Nothing known about the precedence of '%s'" % (p.file,p.line,precname) + sys.stderr.write("%s:%d: Nothing known about the precedence of '%s'\n" % (p.file,p.line,precname)) return -1 else: p.prec = prec @@ -692,12 +738,17 @@ def add_function(f): file = f.func_code.co_filename error = 0 - if f.func_code.co_argcount > 1: - print "%s:%d: Rule '%s' has too many arguments." % (file,line,f.__name__) + if isinstance(f,types.MethodType): + reqdargs = 2 + else: + reqdargs = 1 + + if f.func_code.co_argcount > reqdargs: + sys.stderr.write("%s:%d: Rule '%s' has too many arguments.\n" % (file,line,f.__name__)) return -1 - if f.func_code.co_argcount < 1: - print "%s:%d: Rule '%s' requires an argument." % (file,line,f.__name__) + if f.func_code.co_argcount < reqdargs: + sys.stderr.write("%s:%d: Rule '%s' requires an argument.\n" % (file,line,f.__name__)) return -1 if f.__doc__: @@ -713,7 +764,7 @@ def add_function(f): if p[0] == '|': # This is a continuation of a previous rule if not lastp: - print "%s:%d: Misplaced '|'." % (file,dline) + sys.stderr.write("%s:%d: Misplaced '|'.\n" % (file,dline)) return -1 prodname = lastp if len(p) > 1: @@ -729,15 +780,19 @@ def add_function(f): else: syms = [ ] if assign != ':' and assign != '::=': - print "%s:%d: Syntax error. Expected ':'" % (file,dline) + sys.stderr.write("%s:%d: Syntax error. Expected ':'\n" % (file,dline)) return -1 + + e = add_production(f,file,dline,prodname,syms) error += e + + except StandardError: - print "%s:%d: Syntax error in rule '%s'" % (file,dline,ps) + sys.stderr.write("%s:%d: Syntax error in rule '%s'\n" % (file,dline,ps)) error -= 1 else: - print "%s:%d: No documentation string specified in function '%s'" % (file,line,f.__name__) + sys.stderr.write("%s:%d: No documentation string specified in function '%s'\n" % (file,line,f.__name__)) return error @@ -757,7 +812,7 @@ def compute_reachable(): for s in Nonterminals.keys(): if not Reachable[s]: - print "yacc: Symbol '%s' is unreachable." % s + sys.stderr.write("yacc: Symbol '%s' is unreachable.\n" % s) def mark_reachable_from(s, Reachable): ''' @@ -788,7 +843,7 @@ def compute_terminates(): for t in Terminals.keys(): Terminates[t] = 1 - Terminates['$'] = 1 + Terminates['$end'] = 1 # Nonterminals: @@ -834,7 +889,7 @@ def compute_terminates(): # so it would be overkill to say that it's also non-terminating. pass else: - print "yacc: Infinite recursion detected for symbol '%s'." % s + sys.stderr.write("yacc: Infinite recursion detected for symbol '%s'.\n" % s) some_error = 1 return some_error @@ -851,7 +906,7 @@ def verify_productions(cycle_check=1): for s in p.prod: if not Prodnames.has_key(s) and not Terminals.has_key(s) and s != 'error': - print "%s:%d: Symbol '%s' used, but not defined as a token or a rule." % (p.file,p.line,s) + sys.stderr.write("%s:%d: Symbol '%s' used, but not defined as a token or a rule.\n" % (p.file,p.line,s)) error = 1 continue @@ -861,7 +916,7 @@ def verify_productions(cycle_check=1): _vf.write("Unused terminals:\n\n") for s,v in Terminals.items(): if s != 'error' and not v: - print "yacc: Warning. Token '%s' defined, but not used." % s + sys.stderr.write("yacc: Warning. Token '%s' defined, but not used.\n" % s) if yaccdebug: _vf.write(" %s\n"% s) unused_tok += 1 @@ -876,19 +931,19 @@ def verify_productions(cycle_check=1): for s,v in Nonterminals.items(): if not v: p = Prodnames[s][0] - print "%s:%d: Warning. Rule '%s' defined, but not used." % (p.file,p.line, s) + sys.stderr.write("%s:%d: Warning. Rule '%s' defined, but not used.\n" % (p.file,p.line, s)) unused_prod += 1 if unused_tok == 1: - print "yacc: Warning. There is 1 unused token." + sys.stderr.write("yacc: Warning. There is 1 unused token.\n") if unused_tok > 1: - print "yacc: Warning. There are %d unused tokens." % unused_tok + sys.stderr.write("yacc: Warning. There are %d unused tokens.\n" % unused_tok) if unused_prod == 1: - print "yacc: Warning. There is 1 unused rule." + sys.stderr.write("yacc: Warning. There is 1 unused rule.\n") if unused_prod > 1: - print "yacc: Warning. There are %d unused rules." % unused_prod + sys.stderr.write("yacc: Warning. There are %d unused rules.\n" % unused_prod) if yaccdebug: _vf.write("\nTerminals, with rules where they appear\n\n") @@ -957,16 +1012,16 @@ def add_precedence(plist): prec = p[0] terms = p[1:] if prec != 'left' and prec != 'right' and prec != 'nonassoc': - print "yacc: Invalid precedence '%s'" % prec + sys.stderr.write("yacc: Invalid precedence '%s'\n" % prec) return -1 for t in terms: if Precedence.has_key(t): - print "yacc: Precedence already specified for terminal '%s'" % t + sys.stderr.write("yacc: Precedence already specified for terminal '%s'\n" % t) error += 1 continue Precedence[t] = (prec,plevel) except: - print "yacc: Invalid precedence table." + sys.stderr.write("yacc: Invalid precedence table.\n") error += 1 return error @@ -1029,14 +1084,14 @@ def first(beta): # that might follow it. Dragon book, p. 189. def compute_follow(start=None): - # Add '$' to the follow list of the start symbol + # Add '$end' to the follow list of the start symbol for k in Nonterminals.keys(): Follow[k] = [ ] if not start: start = Productions[1].name - Follow[start] = [ '$' ] + Follow[start] = [ '$end' ] while 1: didadd = 0 @@ -1078,7 +1133,7 @@ def compute_first1(): for t in Terminals.keys(): First[t] = [t] - First['$'] = ['$'] + First['$end'] = ['$end'] First['#'] = ['#'] # what's this for? # Nonterminals: @@ -1115,12 +1170,14 @@ def compute_first1(): # Global variables for the LR parsing engine def lr_init_vars(): global _lr_action, _lr_goto, _lr_method - global _lr_goto_cache + global _lr_goto_cache, _lr0_cidhash _lr_action = { } # Action table _lr_goto = { } # Goto table _lr_method = "Unknown" # LR method used _lr_goto_cache = { } + _lr0_cidhash = { } + # Compute the LR(0) closure operation on I, where I is a set of LR(0) items. # prodlist is a list of productions. @@ -1178,25 +1235,16 @@ def lr0_goto(I,x): s[id(n)] = s1 gs.append(n) s = s1 - g = s.get('$',None) + g = s.get('$end',None) if not g: if gs: g = lr0_closure(gs) - s['$'] = g + s['$end'] = g else: - s['$'] = gs + s['$end'] = gs _lr_goto_cache[(id(I),x)] = g return g -# Compute the kernel of a set of LR(0) items -def lr0_kernel(I): - KI = [ ] - for p in I: - if p.name == "S'" or p.lr_index > 0 or p.len == 0: - KI.append(p) - - return KI - _lr0_cidhash = { } # Compute the LR(0) sets of item function @@ -1230,35 +1278,386 @@ def lr0_items(): return C # ----------------------------------------------------------------------------- -# slr_parse_table() +# ==== LALR(1) Parsing ==== +# +# LALR(1) parsing is almost exactly the same as SLR except that instead of +# relying upon Follow() sets when performing reductions, a more selective +# lookahead set that incorporates the state of the LR(0) machine is utilized. +# Thus, we mainly just have to focus on calculating the lookahead sets. +# +# The method used here is due to DeRemer and Pennelo (1982). +# +# DeRemer, F. L., and T. J. Pennelo: "Efficient Computation of LALR(1) +# Lookahead Sets", ACM Transactions on Programming Languages and Systems, +# Vol. 4, No. 4, Oct. 1982, pp. 615-649 +# +# Further details can also be found in: +# +# J. Tremblay and P. Sorenson, "The Theory and Practice of Compiler Writing", +# McGraw-Hill Book Company, (1985). +# +# Note: This implementation is a complete replacement of the LALR(1) +# implementation in PLY-1.x releases. That version was based on +# a less efficient algorithm and it had bugs in its implementation. +# ----------------------------------------------------------------------------- + +# ----------------------------------------------------------------------------- +# compute_nullable_nonterminals() +# +# Creates a dictionary containing all of the non-terminals that might produce +# an empty production. +# ----------------------------------------------------------------------------- + +def compute_nullable_nonterminals(): + nullable = {} + num_nullable = 0 + while 1: + for p in Productions[1:]: + if p.len == 0: + nullable[p.name] = 1 + continue + for t in p.prod: + if not nullable.has_key(t): break + else: + nullable[p.name] = 1 + if len(nullable) == num_nullable: break + num_nullable = len(nullable) + return nullable + +# ----------------------------------------------------------------------------- +# find_nonterminal_trans(C) +# +# Given a set of LR(0) items, this functions finds all of the non-terminal +# transitions. These are transitions in which a dot appears immediately before +# a non-terminal. Returns a list of tuples of the form (state,N) where state +# is the state number and N is the nonterminal symbol. +# +# The input C is the set of LR(0) items. +# ----------------------------------------------------------------------------- + +def find_nonterminal_transitions(C): + trans = [] + for state in range(len(C)): + for p in C[state]: + if p.lr_index < p.len - 1: + t = (state,p.prod[p.lr_index+1]) + if Nonterminals.has_key(t[1]): + if t not in trans: trans.append(t) + state = state + 1 + return trans + +# ----------------------------------------------------------------------------- +# dr_relation() +# +# Computes the DR(p,A) relationships for non-terminal transitions. The input +# is a tuple (state,N) where state is a number and N is a nonterminal symbol. +# +# Returns a list of terminals. +# ----------------------------------------------------------------------------- + +def dr_relation(C,trans,nullable): + dr_set = { } + state,N = trans + terms = [] + + g = lr0_goto(C[state],N) + for p in g: + if p.lr_index < p.len - 1: + a = p.prod[p.lr_index+1] + if Terminals.has_key(a): + if a not in terms: terms.append(a) + + # This extra bit is to handle the start state + if state == 0 and N == Productions[0].prod[0]: + terms.append('$end') + + return terms + +# ----------------------------------------------------------------------------- +# reads_relation() +# +# Computes the READS() relation (p,A) READS (t,C). +# ----------------------------------------------------------------------------- + +def reads_relation(C, trans, empty): + # Look for empty transitions + rel = [] + state, N = trans + + g = lr0_goto(C[state],N) + j = _lr0_cidhash.get(id(g),-1) + for p in g: + if p.lr_index < p.len - 1: + a = p.prod[p.lr_index + 1] + if empty.has_key(a): + rel.append((j,a)) + + return rel + +# ----------------------------------------------------------------------------- +# compute_lookback_includes() +# +# Determines the lookback and includes relations +# +# LOOKBACK: +# +# This relation is determined by running the LR(0) state machine forward. +# For example, starting with a production "N : . A B C", we run it forward +# to obtain "N : A B C ." We then build a relationship between this final +# state and the starting state. These relationships are stored in a dictionary +# lookdict. +# +# INCLUDES: +# +# Computes the INCLUDE() relation (p,A) INCLUDES (p',B). +# +# This relation is used to determine non-terminal transitions that occur +# inside of other non-terminal transition states. (p,A) INCLUDES (p', B) +# if the following holds: # -# This function constructs an SLR table. +# B -> LAT, where T -> epsilon and p' -L-> p +# +# L is essentially a prefix (which may be empty), T is a suffix that must be +# able to derive an empty string. State p' must lead to state p with the string L. +# +# ----------------------------------------------------------------------------- + +def compute_lookback_includes(C,trans,nullable): + + lookdict = {} # Dictionary of lookback relations + includedict = {} # Dictionary of include relations + + # Make a dictionary of non-terminal transitions + dtrans = {} + for t in trans: + dtrans[t] = 1 + + # Loop over all transitions and compute lookbacks and includes + for state,N in trans: + lookb = [] + includes = [] + for p in C[state]: + if p.name != N: continue + + # Okay, we have a name match. We now follow the production all the way + # through the state machine until we get the . on the right hand side + + lr_index = p.lr_index + j = state + while lr_index < p.len - 1: + lr_index = lr_index + 1 + t = p.prod[lr_index] + + # Check to see if this symbol and state are a non-terminal transition + if dtrans.has_key((j,t)): + # Yes. Okay, there is some chance that this is an includes relation + # the only way to know for certain is whether the rest of the + # production derives empty + + li = lr_index + 1 + while li < p.len: + if Terminals.has_key(p.prod[li]): break # No forget it + if not nullable.has_key(p.prod[li]): break + li = li + 1 + else: + # Appears to be a relation between (j,t) and (state,N) + includes.append((j,t)) + + g = lr0_goto(C[j],t) # Go to next set + j = _lr0_cidhash.get(id(g),-1) # Go to next state + + # When we get here, j is the final state, now we have to locate the production + for r in C[j]: + if r.name != p.name: continue + if r.len != p.len: continue + i = 0 + # This look is comparing a production ". A B C" with "A B C ." + while i < r.lr_index: + if r.prod[i] != p.prod[i+1]: break + i = i + 1 + else: + lookb.append((j,r)) + for i in includes: + if not includedict.has_key(i): includedict[i] = [] + includedict[i].append((state,N)) + lookdict[(state,N)] = lookb + + return lookdict,includedict + # ----------------------------------------------------------------------------- -def slr_parse_table(): +# digraph() +# traverse() +# +# The following two functions are used to compute set valued functions +# of the form: +# +# F(x) = F'(x) U U{F(y) | x R y} +# +# This is used to compute the values of Read() sets as well as FOLLOW sets +# in LALR(1) generation. +# +# Inputs: X - An input set +# R - A relation +# FP - Set-valued function +# ------------------------------------------------------------------------------ + +def digraph(X,R,FP): + N = { } + for x in X: + N[x] = 0 + stack = [] + F = { } + for x in X: + if N[x] == 0: traverse(x,N,stack,F,X,R,FP) + return F + +def traverse(x,N,stack,F,X,R,FP): + stack.append(x) + d = len(stack) + N[x] = d + F[x] = FP(x) # F(X) <- F'(x) + + rel = R(x) # Get y's related to x + for y in rel: + if N[y] == 0: + traverse(y,N,stack,F,X,R,FP) + N[x] = min(N[x],N[y]) + for a in F.get(y,[]): + if a not in F[x]: F[x].append(a) + if N[x] == d: + N[stack[-1]] = sys.maxint + F[stack[-1]] = F[x] + element = stack.pop() + while element != x: + N[stack[-1]] = sys.maxint + F[stack[-1]] = F[x] + element = stack.pop() + +# ----------------------------------------------------------------------------- +# compute_read_sets() +# +# Given a set of LR(0) items, this function computes the read sets. +# +# Inputs: C = Set of LR(0) items +# ntrans = Set of nonterminal transitions +# nullable = Set of empty transitions +# +# Returns a set containing the read sets +# ----------------------------------------------------------------------------- + +def compute_read_sets(C, ntrans, nullable): + FP = lambda x: dr_relation(C,x,nullable) + R = lambda x: reads_relation(C,x,nullable) + F = digraph(ntrans,R,FP) + return F + +# ----------------------------------------------------------------------------- +# compute_follow_sets() +# +# Given a set of LR(0) items, a set of non-terminal transitions, a readset, +# and an include set, this function computes the follow sets +# +# Follow(p,A) = Read(p,A) U U {Follow(p',B) | (p,A) INCLUDES (p',B)} +# +# Inputs: +# ntrans = Set of nonterminal transitions +# readsets = Readset (previously computed) +# inclsets = Include sets (previously computed) +# +# Returns a set containing the follow sets +# ----------------------------------------------------------------------------- + +def compute_follow_sets(ntrans,readsets,inclsets): + FP = lambda x: readsets[x] + R = lambda x: inclsets.get(x,[]) + F = digraph(ntrans,R,FP) + return F + +# ----------------------------------------------------------------------------- +# add_lookaheads() +# +# Attaches the lookahead symbols to grammar rules. +# +# Inputs: lookbacks - Set of lookback relations +# followset - Computed follow set +# +# This function directly attaches the lookaheads to productions contained +# in the lookbacks set +# ----------------------------------------------------------------------------- + +def add_lookaheads(lookbacks,followset): + for trans,lb in lookbacks.items(): + # Loop over productions in lookback + for state,p in lb: + if not p.lookaheads.has_key(state): + p.lookaheads[state] = [] + f = followset.get(trans,[]) + for a in f: + if a not in p.lookaheads[state]: p.lookaheads[state].append(a) + +# ----------------------------------------------------------------------------- +# add_lalr_lookaheads() +# +# This function does all of the work of adding lookahead information for use +# with LALR parsing +# ----------------------------------------------------------------------------- + +def add_lalr_lookaheads(C): + # Determine all of the nullable nonterminals + nullable = compute_nullable_nonterminals() + + # Find all non-terminal transitions + trans = find_nonterminal_transitions(C) + + # Compute read sets + readsets = compute_read_sets(C,trans,nullable) + + # Compute lookback/includes relations + lookd, included = compute_lookback_includes(C,trans,nullable) + + # Compute LALR FOLLOW sets + followsets = compute_follow_sets(trans,readsets,included) + + # Add all of the lookaheads + add_lookaheads(lookd,followsets) + +# ----------------------------------------------------------------------------- +# lr_parse_table() +# +# This function constructs the parse tables for SLR or LALR +# ----------------------------------------------------------------------------- +def lr_parse_table(method): global _lr_method goto = _lr_goto # Goto array action = _lr_action # Action array actionp = { } # Action production array (temporary) - _lr_method = "SLR" + _lr_method = method n_srconflict = 0 n_rrconflict = 0 if yaccdebug: - _vf.write("\n\nParsing method: SLR\n\n") + sys.stderr.write("yacc: Generating %s parsing table...\n" % method) + _vf.write("\n\nParsing method: %s\n\n" % method) # Step 1: Construct C = { I0, I1, ... IN}, collection of LR(0) items # This determines the number of states C = lr0_items() + if method == 'LALR': + add_lalr_lookaheads(C) + + # Build the parser table, state by state st = 0 for I in C: # Loop over each production in I actlist = [ ] # List of actions - + st_action = { } + st_actionp = { } + st_goto = { } if yaccdebug: _vf.write("\nstate %d\n\n" % st) for p in I: @@ -1267,37 +1666,41 @@ def slr_parse_table(): for p in I: try: - if p.prod[-1] == ".": + if p.len == p.lr_index + 1: if p.name == "S'": # Start symbol. Accept! - action[st,"$"] = 0 - actionp[st,"$"] = p + st_action["$end"] = 0 + st_actionp["$end"] = p else: # We are at the end of a production. Reduce! - for a in Follow[p.name]: + if method == 'LALR': + laheads = p.lookaheads[st] + else: + laheads = Follow[p.name] + for a in laheads: actlist.append((a,p,"reduce using rule %d (%s)" % (p.number,p))) - r = action.get((st,a),None) + r = st_action.get(a,None) if r is not None: # Whoa. Have a shift/reduce or reduce/reduce conflict if r > 0: # Need to decide on shift or reduce here # By default we favor shifting. Need to add # some precedence rules here. - sprec,slevel = Productions[actionp[st,a].number].prec + sprec,slevel = Productions[st_actionp[a].number].prec rprec,rlevel = Precedence.get(a,('right',0)) if (slevel < rlevel) or ((slevel == rlevel) and (rprec == 'left')): # We really need to reduce here. - action[st,a] = -p.number - actionp[st,a] = p + st_action[a] = -p.number + st_actionp[a] = p if not slevel and not rlevel: _vfc.write("shift/reduce conflict in state %d resolved as reduce.\n" % st) _vf.write(" ! shift/reduce conflict for %s resolved as reduce.\n" % a) n_srconflict += 1 elif (slevel == rlevel) and (rprec == 'nonassoc'): - action[st,a] = None + st_action[a] = None else: # Hmmm. Guess we'll keep the shift - if not slevel and not rlevel: + if not rlevel: _vfc.write("shift/reduce conflict in state %d resolved as shift.\n" % st) _vf.write(" ! shift/reduce conflict for %s resolved as shift.\n" % a) n_srconflict +=1 @@ -1307,17 +1710,17 @@ def slr_parse_table(): oldp = Productions[-r] pp = Productions[p.number] if oldp.line > pp.line: - action[st,a] = -p.number - actionp[st,a] = p - # print "Reduce/reduce conflict in state %d" % st + st_action[a] = -p.number + st_actionp[a] = p + # sys.stderr.write("Reduce/reduce conflict in state %d\n" % st) n_rrconflict += 1 - _vfc.write("reduce/reduce conflict in state %d resolved using rule %d (%s).\n" % (st, actionp[st,a].number, actionp[st,a])) - _vf.write(" ! reduce/reduce conflict for %s resolved using rule %d (%s).\n" % (a,actionp[st,a].number, actionp[st,a])) + _vfc.write("reduce/reduce conflict in state %d resolved using rule %d (%s).\n" % (st, st_actionp[a].number, st_actionp[a])) + _vf.write(" ! reduce/reduce conflict for %s resolved using rule %d (%s).\n" % (a,st_actionp[a].number, st_actionp[a])) else: - print "Unknown conflict in state %d" % st + sys.stderr.write("Unknown conflict in state %d\n" % st) else: - action[st,a] = -p.number - actionp[st,a] = p + st_action[a] = -p.number + st_actionp[a] = p else: i = p.lr_index a = p.prod[i+1] # Get symbol right after the "." @@ -1327,29 +1730,29 @@ def slr_parse_table(): if j >= 0: # We are in a shift state actlist.append((a,p,"shift and go to state %d" % j)) - r = action.get((st,a),None) + r = st_action.get(a,None) if r is not None: # Whoa have a shift/reduce or shift/shift conflict if r > 0: if r != j: - print "Shift/shift conflict in state %d" % st + sys.stderr.write("Shift/shift conflict in state %d\n" % st) elif r < 0: # Do a precedence check. # - if precedence of reduce rule is higher, we reduce. # - if precedence of reduce is same and left assoc, we reduce. # - otherwise we shift - rprec,rlevel = Productions[actionp[st,a].number].prec + rprec,rlevel = Productions[st_actionp[a].number].prec sprec,slevel = Precedence.get(a,('right',0)) if (slevel > rlevel) or ((slevel == rlevel) and (rprec != 'left')): # We decide to shift here... highest precedence to shift - action[st,a] = j - actionp[st,a] = p - if not slevel and not rlevel: + st_action[a] = j + st_actionp[a] = p + if not rlevel: n_srconflict += 1 _vfc.write("shift/reduce conflict in state %d resolved as shift.\n" % st) _vf.write(" ! shift/reduce conflict for %s resolved as shift.\n" % a) elif (slevel == rlevel) and (rprec == 'nonassoc'): - action[st,a] = None + st_action[a] = None else: # Hmmm. Guess we'll keep the reduce if not slevel and not rlevel: @@ -1358,25 +1761,30 @@ def slr_parse_table(): _vf.write(" ! shift/reduce conflict for %s resolved as reduce.\n" % a) else: - print "Unknown conflict in state %d" % st + sys.stderr.write("Unknown conflict in state %d\n" % st) else: - action[st,a] = j - actionp[st,a] = p + st_action[a] = j + st_actionp[a] = p except StandardError,e: - raise YaccError, "Hosed in slr_parse_table", e + print sys.exc_info() + raise YaccError, "Hosed in lr_parse_table" # Print the actions associated with each terminal if yaccdebug: + _actprint = { } for a,p,m in actlist: - if action.has_key((st,a)): - if p is actionp[st,a]: + if st_action.has_key(a): + if p is st_actionp[a]: _vf.write(" %-15s %s\n" % (a,m)) + _actprint[(a,m)] = 1 _vf.write("\n") for a,p,m in actlist: - if action.has_key((st,a)): - if p is not actionp[st,a]: - _vf.write(" ! %-15s [ %s ]\n" % (a,m)) + if st_action.has_key(a): + if p is not st_actionp[a]: + if not _actprint.has_key((a,m)): + _vf.write(" ! %-15s [ %s ]\n" % (a,m)) + _actprint[(a,m)] = 1 # Construct the goto table for this state if yaccdebug: @@ -1390,82 +1798,25 @@ def slr_parse_table(): g = lr0_goto(I,n) j = _lr0_cidhash.get(id(g),-1) if j >= 0: - goto[st,n] = j + st_goto[n] = j if yaccdebug: - _vf.write(" %-15s shift and go to state %d\n" % (n,j)) + _vf.write(" %-30s shift and go to state %d\n" % (n,j)) - st += 1 + action[st] = st_action + actionp[st] = st_actionp + goto[st] = st_goto - if n_srconflict == 1: - print "yacc: %d shift/reduce conflict" % n_srconflict - if n_srconflict > 1: - print "yacc: %d shift/reduce conflicts" % n_srconflict - if n_rrconflict == 1: - print "yacc: %d reduce/reduce conflict" % n_rrconflict - if n_rrconflict > 1: - print "yacc: %d reduce/reduce conflicts" % n_rrconflict - - -# ----------------------------------------------------------------------------- -# ==== LALR(1) Parsing ==== -# **** UNFINISHED! 6/16/01 -# ----------------------------------------------------------------------------- - - -# Compute the lr1_closure of a set I. I is a list of tuples (p,a) where -# p is a LR0 item and a is a terminal - -_lr1_add_count = 0 - -def lr1_closure(I): - global _lr1_add_count - - _lr1_add_count += 1 - - J = I[:] - - # Loop over items (p,a) in I. - ji = 0 - while ji < len(J): - p,a = J[ji] - # p = [ A -> alpha . B beta] - - # For each production B -> gamma - for B in p.lr1_after: - f = tuple(p.lr1_beta + (a,)) - - # For each terminal b in first(Beta a) - for b in first(f): - # Check if (B -> . gamma, b) is in J - # Only way this can happen is if the add count mismatches - pn = B.lr_next - if pn.lr_added.get(b,0) == _lr1_add_count: continue - pn.lr_added[b] = _lr1_add_count - J.append((pn,b)) - ji += 1 - - return J - -def lalr_parse_table(): - - # Compute some lr1 information about all of the productions - for p in LRitems: - try: - after = p.prod[p.lr_index + 1] - p.lr1_after = Prodnames[after] - p.lr1_beta = p.prod[p.lr_index + 2:] - except LookupError: - p.lr1_after = [ ] - p.lr1_beta = [ ] - p.lr_added = { } - - # Compute the LR(0) items - C = lr0_items() - CK = [] - for I in C: - CK.append(lr0_kernel(I)) + st += 1 - print CK + if yaccdebug: + if n_srconflict == 1: + sys.stderr.write("yacc: %d shift/reduce conflict\n" % n_srconflict) + if n_srconflict > 1: + sys.stderr.write("yacc: %d shift/reduce conflicts\n" % n_srconflict) + if n_rrconflict == 1: + sys.stderr.write("yacc: %d reduce/reduce conflict\n" % n_rrconflict) + if n_rrconflict > 1: + sys.stderr.write("yacc: %d reduce/reduce conflicts\n" % n_rrconflict) # ----------------------------------------------------------------------------- # ==== LR Utility functions ==== @@ -1477,8 +1828,8 @@ def lalr_parse_table(): # This function writes the LR parsing tables to a file # ----------------------------------------------------------------------------- -def lr_write_tables(modulename=tab_module): - filename = modulename + ".py" +def lr_write_tables(modulename=tab_module,outputdir=''): + filename = os.path.join(outputdir,modulename) + ".py" try: f = open(filename,"w") @@ -1498,13 +1849,14 @@ _lr_signature = %s if smaller: items = { } - for k,v in _lr_action.items(): - i = items.get(k[1]) - if not i: - i = ([],[]) - items[k[1]] = i - i[0].append(k[0]) - i[1].append(v) + for s,nd in _lr_action.items(): + for name,v in nd.items(): + i = items.get(name) + if not i: + i = ([],[]) + items[name] = i + i[0].append(s) + i[1].append(v) f.write("\n_lr_action_items = {") for k,v in items.items(): @@ -1522,7 +1874,8 @@ _lr_signature = %s _lr_action = { } for _k, _v in _lr_action_items.items(): for _x,_y in zip(_v[0],_v[1]): - _lr_action[(_x,_k)] = _y + if not _lr_action.has_key(_x): _lr_action[_x] = { } + _lr_action[_x][_k] = _y del _lr_action_items """) @@ -1536,13 +1889,14 @@ del _lr_action_items # Factor out names to try and make smaller items = { } - for k,v in _lr_goto.items(): - i = items.get(k[1]) - if not i: - i = ([],[]) - items[k[1]] = i - i[0].append(k[0]) - i[1].append(v) + for s,nd in _lr_goto.items(): + for name,v in nd.items(): + i = items.get(name) + if not i: + i = ([],[]) + items[name] = i + i[0].append(s) + i[1].append(v) f.write("\n_lr_goto_items = {") for k,v in items.items(): @@ -1560,7 +1914,8 @@ del _lr_action_items _lr_goto = { } for _k, _v in _lr_goto_items.items(): for _x,_y in zip(_v[0],_v[1]): - _lr_goto[(_x,_k)] = _y + if not _lr_goto.has_key(_x): _lr_goto[_x] = { } + _lr_goto[_x][_k] = _y del _lr_goto_items """) else: @@ -1580,11 +1935,12 @@ del _lr_goto_items else: f.write(" None,\n") f.write("]\n") + f.close() except IOError,e: - print "Unable to create '%s'" % filename - print e + print >>sys.stderr, "Unable to create '%s'" % filename + print >>sys.stderr, e return def lr_read_tables(module=tab_module,optimize=0): @@ -1604,13 +1960,14 @@ def lr_read_tables(module=tab_module,optimize=0): except (ImportError,AttributeError): return 0 + # ----------------------------------------------------------------------------- # yacc(module) # # Build the parser module # ----------------------------------------------------------------------------- -def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, start=None, check_recursion=1, optimize=0): +def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, start=None, check_recursion=1, optimize=0,write_tables=1,debugfile=debug_file,outputdir=''): global yaccdebug yaccdebug = debug @@ -1618,18 +1975,25 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, files = { } error = 0 - # Add starting symbol to signature - if start: - Signature.update(start) - # Try to figure out what module we are working with + # Add parsing method to signature + Signature.update(method) + + # If a "module" parameter was supplied, extract its dictionary. + # Note: a module may in fact be an instance as well. + if module: # User supplied a module object. - if not isinstance(module, types.ModuleType): + 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 in _items: + ldict[i[0]] = i[1] + else: raise ValueError,"Expected a module" - ldict = module.__dict__ - else: # No module given. We might be able to get information from the caller. # Throw an exception and unwind the traceback to get the globals @@ -1642,6 +2006,12 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, f = f.f_back # Walk out to our calling function ldict = f.f_globals # Grab its globals dictionary + # Add starting symbol to signature + if not start: + start = ldict.get("start",None) + if start: + Signature.update(start) + # If running in optimized mode. We're going to if (optimize and lr_read_tables(tabmodule,1)): @@ -1662,7 +2032,10 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, else: # Get the tokens map - tokens = ldict.get("tokens",None) + if (module and isinstance(module,_INSTANCETYPE)): + tokens = getattr(module,"tokens",None) + else: + tokens = ldict.get("tokens",None) if not tokens: raise YaccError,"module does not define a list 'tokens'" @@ -1682,7 +2055,7 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, v1 = [x.split(".") for x in v] Requires[r] = v1 except StandardError: - print "Invalid specification for rule '%s' in require. Expected a list of strings" % r + print >>sys.stderr, "Invalid specification for rule '%s' in require. Expected a list of strings" % r # Build the dictionary of terminals. We a record a 0 in the @@ -1690,12 +2063,12 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, # used in the grammar if 'error' in tokens: - print "yacc: Illegal token 'error'. Is a reserved word." + print >>sys.stderr, "yacc: Illegal token 'error'. Is a reserved word." raise YaccError,"Illegal token name" for n in tokens: if Terminals.has_key(n): - print "yacc: Warning. Token '%s' multiply defined." % n + print >>sys.stderr, "yacc: Warning. Token '%s' multiply defined." % n Terminals[n] = [ ] Terminals['error'] = [ ] @@ -1715,22 +2088,26 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, # Look for error handler ef = ldict.get('p_error',None) if ef: - if not isinstance(ef,types.FunctionType): - raise YaccError,"'p_error' defined, but is not a function." + if isinstance(ef,types.FunctionType): + ismethod = 0 + elif isinstance(ef, types.MethodType): + ismethod = 1 + else: + raise YaccError,"'p_error' defined, but is not a function or method." eline = ef.func_code.co_firstlineno efile = ef.func_code.co_filename files[efile] = None - if (ef.func_code.co_argcount != 1): + if (ef.func_code.co_argcount != 1+ismethod): raise YaccError,"%s:%d: p_error() requires 1 argument." % (efile,eline) global Errorfunc Errorfunc = ef else: - print "yacc: Warning. no p_error() function is defined." + print >>sys.stderr, "yacc: Warning. no p_error() function is defined." # Get the list of built-in functions with p_ prefix symbols = [ldict[f] for f in ldict.keys() - if (isinstance(ldict[f],types.FunctionType) and ldict[f].__name__[:2] == 'p_' + if (type(ldict[f]) in (types.FunctionType, types.MethodType) and ldict[f].__name__[:2] == 'p_' and ldict[f].__name__ != 'p_error')] # Check for non-empty symbols @@ -1773,7 +2150,7 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, augment_grammar(start) error = verify_productions(cycle_check=check_recursion) otherfunc = [ldict[f] for f in ldict.keys() - if (isinstance(ldict[f],types.FunctionType) and ldict[f].__name__[:2] != 'p_')] + if (type(f) in (types.FunctionType,types.MethodType) and ldict[f].__name__[:2] != 'p_')] if error: raise YaccError,"Unable to construct parser." @@ -1782,25 +2159,23 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, compute_first1() compute_follow(start) - if method == 'SLR': - slr_parse_table() - elif method == 'LALR1': - lalr_parse_table() - return + if method in ['SLR','LALR']: + lr_parse_table(method) else: raise YaccError, "Unknown parsing method '%s'" % method - lr_write_tables(tabmodule) + if write_tables: + lr_write_tables(tabmodule,outputdir) if yaccdebug: try: - f = open(debug_file,"w") + f = open(os.path.join(outputdir,debugfile),"w") f.write(_vfc.getvalue()) f.write("\n\n") f.write(_vf.getvalue()) f.close() except IOError,e: - print "yacc: can't create '%s'" % debug_file,e + print >>sys.stderr, "yacc: can't create '%s'" % debugfile,e # Made it here. Create a parser object and set up its internal state. # Set global parse() method to bound method of parser object. @@ -1816,6 +2191,9 @@ def yacc(method=default_lr, debug=yaccdebug, module=None, tabmodule=tab_module, global parse parse = p.parse + global parser + parser = p + # Clean up all of the globals we created if (not optimize): yacc_cleanup() diff --git a/ext/ply/setup.py b/ext/ply/setup.py new file mode 100644 index 000000000..f743ac78c --- /dev/null +++ b/ext/ply/setup.py @@ -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'], + ) diff --git a/ext/ply/test/README b/ext/ply/test/README index bca748497..aac12b058 100644 --- a/ext/ply/test/README +++ b/ext/ply/test/README @@ -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. diff --git a/ext/ply/test/calclex.py b/ext/ply/test/calclex.py index f8eb91a09..d3e873266 100644 --- a/ext/ply/test/calclex.py +++ b/ext/ply/test/calclex.py @@ -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() diff --git a/ext/ply/test/cleanup.sh b/ext/ply/test/cleanup.sh new file mode 100644 index 000000000..d7d99b65f --- /dev/null +++ b/ext/ply/test/cleanup.sh @@ -0,0 +1,4 @@ +#!/bin/sh + +rm -f *~ *.pyc *.dif *.out + diff --git a/ext/ply/test/lex_doc1.exp b/ext/ply/test/lex_doc1.exp index 29381911d..5b63c1e91 100644 --- a/ext/ply/test/lex_doc1.exp +++ b/ext/ply/test/lex_doc1.exp @@ -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' diff --git a/ext/ply/test/lex_doc1.py b/ext/ply/test/lex_doc1.py index fb0fb885e..3951b5c5d 100644 --- a/ext/ply/test/lex_doc1.py +++ b/ext/ply/test/lex_doc1.py @@ -2,7 +2,10 @@ # # Missing documentation string -import lex +import sys +sys.path.insert(0,"..") + +import ply.lex as lex tokens = [ "PLUS", diff --git a/ext/ply/test/lex_dup1.exp b/ext/ply/test/lex_dup1.exp index 22bca3190..2098a40e5 100644 --- a/ext/ply/test/lex_dup1.exp +++ b/ext/ply/test/lex_dup1.exp @@ -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. diff --git a/ext/ply/test/lex_dup1.py b/ext/ply/test/lex_dup1.py index 88bbe00e9..68f80925b 100644 --- a/ext/ply/test/lex_dup1.py +++ b/ext/ply/test/lex_dup1.py @@ -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() diff --git a/ext/ply/test/lex_dup2.exp b/ext/ply/test/lex_dup2.exp index 883bdad46..d327cfe47 100644 --- a/ext/ply/test/lex_dup2.exp +++ b/ext/ply/test/lex_dup2.exp @@ -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. diff --git a/ext/ply/test/lex_dup2.py b/ext/ply/test/lex_dup2.py index 65e0b21a2..f4d346e75 100644 --- a/ext/ply/test/lex_dup2.py +++ b/ext/ply/test/lex_dup2.py @@ -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() diff --git a/ext/ply/test/lex_dup3.exp b/ext/ply/test/lex_dup3.exp index 916612aa1..ec0680c6c 100644 --- a/ext/ply/test/lex_dup3.exp +++ b/ext/ply/test/lex_dup3.exp @@ -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. diff --git a/ext/ply/test/lex_dup3.py b/ext/ply/test/lex_dup3.py index 424101823..e17b52059 100644 --- a/ext/ply/test/lex_dup3.py +++ b/ext/ply/test/lex_dup3.py @@ -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() diff --git a/ext/ply/test/lex_empty.py b/ext/ply/test/lex_empty.py index 6472832f1..96625f732 100644 --- a/ext/ply/test/lex_empty.py +++ b/ext/ply/test/lex_empty.py @@ -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() diff --git a/ext/ply/test/lex_error1.py b/ext/ply/test/lex_error1.py index ed7980346..a99d9bedf 100644 --- a/ext/ply/test/lex_error1.py +++ b/ext/ply/test/lex_error1.py @@ -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() diff --git a/ext/ply/test/lex_error2.py b/ext/ply/test/lex_error2.py index 80020f72b..a59c8d454 100644 --- a/ext/ply/test/lex_error2.py +++ b/ext/ply/test/lex_error2.py @@ -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() diff --git a/ext/ply/test/lex_error3.exp b/ext/ply/test/lex_error3.exp index 936828f93..1b482bf62 100644 --- a/ext/ply/test/lex_error3.exp +++ b/ext/ply/test/lex_error3.exp @@ -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. diff --git a/ext/ply/test/lex_error3.py b/ext/ply/test/lex_error3.py index 46facf589..584600f3b 100644 --- a/ext/ply/test/lex_error3.py +++ b/ext/ply/test/lex_error3.py @@ -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() diff --git a/ext/ply/test/lex_error4.exp b/ext/ply/test/lex_error4.exp index 242516576..98505a232 100644 --- a/ext/ply/test/lex_error4.exp +++ b/ext/ply/test/lex_error4.exp @@ -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. diff --git a/ext/ply/test/lex_error4.py b/ext/ply/test/lex_error4.py index d777fee84..d05de7490 100644 --- a/ext/ply/test/lex_error4.py +++ b/ext/ply/test/lex_error4.py @@ -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() diff --git a/ext/ply/test/lex_hedit.exp b/ext/ply/test/lex_hedit.exp index 0b09827c6..7b27dcb57 100644 --- a/ext/ply/test/lex_hedit.exp +++ b/ext/ply/test/lex_hedit.exp @@ -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) diff --git a/ext/ply/test/lex_hedit.py b/ext/ply/test/lex_hedit.py index 68f9fcbd1..9949549c4 100644 --- a/ext/ply/test/lex_hedit.py +++ b/ext/ply/test/lex_hedit.py @@ -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") diff --git a/ext/ply/test/lex_ignore.exp b/ext/ply/test/lex_ignore.exp index c3b04a154..6b6b67cdc 100644 --- a/ext/ply/test/lex_ignore.exp +++ b/ext/ply/test/lex_ignore.exp @@ -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. diff --git a/ext/ply/test/lex_ignore.py b/ext/ply/test/lex_ignore.py index 49c303f81..94b026693 100644 --- a/ext/ply/test/lex_ignore.py +++ b/ext/ply/test/lex_ignore.py @@ -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() diff --git a/ext/ply/test/lex_ignore2.exp b/ext/ply/test/lex_ignore2.exp new file mode 100644 index 000000000..0eb6bf266 --- /dev/null +++ b/ext/ply/test/lex_ignore2.exp @@ -0,0 +1 @@ +lex: Warning. t_ignore contains a literal backslash '\' diff --git a/ext/ply/test/lex_ignore2.py b/ext/ply/test/lex_ignore2.py new file mode 100644 index 000000000..fc95bd1e5 --- /dev/null +++ b/ext/ply/test/lex_ignore2.py @@ -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() + + diff --git a/ext/ply/test/lex_nowarn.py b/ext/ply/test/lex_nowarn.py new file mode 100644 index 000000000..d60d31c53 --- /dev/null +++ b/ext/ply/test/lex_nowarn.py @@ -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) + + diff --git a/ext/ply/test/lex_re1.exp b/ext/ply/test/lex_re1.exp index 634eefefe..4d54f4b89 100644 --- a/ext/ply/test/lex_re1.exp +++ b/ext/ply/test/lex_re1.exp @@ -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. diff --git a/ext/ply/test/lex_re1.py b/ext/ply/test/lex_re1.py index 4a055ad72..9e544fe0d 100644 --- a/ext/ply/test/lex_re1.py +++ b/ext/ply/test/lex_re1.py @@ -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() diff --git a/ext/ply/test/lex_re2.exp b/ext/ply/test/lex_re2.exp new file mode 100644 index 000000000..a4e2e8920 --- /dev/null +++ b/ext/ply/test/lex_re2.exp @@ -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. diff --git a/ext/ply/test/lex_re2.py b/ext/ply/test/lex_re2.py new file mode 100644 index 000000000..522b41592 --- /dev/null +++ b/ext/ply/test/lex_re2.py @@ -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() + + diff --git a/ext/ply/test/lex_re3.exp b/ext/ply/test/lex_re3.exp new file mode 100644 index 000000000..b9ada216d --- /dev/null +++ b/ext/ply/test/lex_re3.exp @@ -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. diff --git a/ext/ply/test/lex_re3.py b/ext/ply/test/lex_re3.py new file mode 100644 index 000000000..099e1568c --- /dev/null +++ b/ext/ply/test/lex_re3.py @@ -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() + + diff --git a/ext/ply/test/lex_rule1.py b/ext/ply/test/lex_rule1.py index ff3764ea1..e49a15bba 100644 --- a/ext/ply/test/lex_rule1.py +++ b/ext/ply/test/lex_rule1.py @@ -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() diff --git a/ext/ply/test/lex_state1.exp b/ext/ply/test/lex_state1.exp new file mode 100644 index 000000000..facad03cc --- /dev/null +++ b/ext/ply/test/lex_state1.exp @@ -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. diff --git a/ext/ply/test/lex_state1.py b/ext/ply/test/lex_state1.py new file mode 100644 index 000000000..887bc2345 --- /dev/null +++ b/ext/ply/test/lex_state1.py @@ -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() + + diff --git a/ext/ply/test/lex_state2.exp b/ext/ply/test/lex_state2.exp new file mode 100644 index 000000000..8b042515a --- /dev/null +++ b/ext/ply/test/lex_state2.exp @@ -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. diff --git a/ext/ply/test/lex_state2.py b/ext/ply/test/lex_state2.py new file mode 100644 index 000000000..3053c7110 --- /dev/null +++ b/ext/ply/test/lex_state2.py @@ -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() + + diff --git a/ext/ply/test/lex_state3.exp b/ext/ply/test/lex_state3.exp new file mode 100644 index 000000000..53ab57ff1 --- /dev/null +++ b/ext/ply/test/lex_state3.exp @@ -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. diff --git a/ext/ply/test/lex_state3.py b/ext/ply/test/lex_state3.py new file mode 100644 index 000000000..bb22d241e --- /dev/null +++ b/ext/ply/test/lex_state3.py @@ -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() + + diff --git a/ext/ply/test/lex_state4.exp b/ext/ply/test/lex_state4.exp new file mode 100644 index 000000000..412ae8f8a --- /dev/null +++ b/ext/ply/test/lex_state4.exp @@ -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. diff --git a/ext/ply/test/lex_state4.py b/ext/ply/test/lex_state4.py new file mode 100644 index 000000000..3815135b4 --- /dev/null +++ b/ext/ply/test/lex_state4.py @@ -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() + + diff --git a/ext/ply/test/lex_state5.exp b/ext/ply/test/lex_state5.exp new file mode 100644 index 000000000..8eeae5641 --- /dev/null +++ b/ext/ply/test/lex_state5.exp @@ -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. diff --git a/ext/ply/test/lex_state5.py b/ext/ply/test/lex_state5.py new file mode 100644 index 000000000..58718538c --- /dev/null +++ b/ext/ply/test/lex_state5.py @@ -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() + + diff --git a/ext/ply/test/lex_state_noerror.exp b/ext/ply/test/lex_state_noerror.exp new file mode 100644 index 000000000..e14149f18 --- /dev/null +++ b/ext/ply/test/lex_state_noerror.exp @@ -0,0 +1 @@ +lex: Warning. no error rule is defined for exclusive state 'comment' diff --git a/ext/ply/test/lex_state_noerror.py b/ext/ply/test/lex_state_noerror.py new file mode 100644 index 000000000..3fda7da49 --- /dev/null +++ b/ext/ply/test/lex_state_noerror.py @@ -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() + + diff --git a/ext/ply/test/lex_state_norule.exp b/ext/ply/test/lex_state_norule.exp new file mode 100644 index 000000000..7097d2a3a --- /dev/null +++ b/ext/ply/test/lex_state_norule.exp @@ -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. diff --git a/ext/ply/test/lex_state_norule.py b/ext/ply/test/lex_state_norule.py new file mode 100644 index 000000000..2f6cabc51 --- /dev/null +++ b/ext/ply/test/lex_state_norule.py @@ -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() + + diff --git a/ext/ply/test/lex_state_try.exp b/ext/ply/test/lex_state_try.exp new file mode 100644 index 000000000..11768b893 --- /dev/null +++ b/ext/ply/test/lex_state_try.exp @@ -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) diff --git a/ext/ply/test/lex_state_try.py b/ext/ply/test/lex_state_try.py new file mode 100644 index 000000000..a2206cbc3 --- /dev/null +++ b/ext/ply/test/lex_state_try.py @@ -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) diff --git a/ext/ply/test/lex_token1.py b/ext/ply/test/lex_token1.py index e8eca2b63..380c31ce1 100644 --- a/ext/ply/test/lex_token1.py +++ b/ext/ply/test/lex_token1.py @@ -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() diff --git a/ext/ply/test/lex_token2.py b/ext/ply/test/lex_token2.py index 38b34dabe..87db8a0ab 100644 --- a/ext/ply/test/lex_token2.py +++ b/ext/ply/test/lex_token2.py @@ -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() diff --git a/ext/ply/test/lex_token3.py b/ext/ply/test/lex_token3.py index 909f9180d..27ce9476d 100644 --- a/ext/ply/test/lex_token3.py +++ b/ext/ply/test/lex_token3.py @@ -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() diff --git a/ext/ply/test/lex_token4.py b/ext/ply/test/lex_token4.py index d77d1662c..612ff13c2 100644 --- a/ext/ply/test/lex_token4.py +++ b/ext/ply/test/lex_token4.py @@ -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() diff --git a/ext/ply/test/lex_token5.exp b/ext/ply/test/lex_token5.exp index d7bcb2e7c..2f038890a 100644 --- a/ext/ply/test/lex_token5.exp +++ b/ext/ply/test/lex_token5.exp @@ -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' diff --git a/ext/ply/test/lex_token5.py b/ext/ply/test/lex_token5.py index d9b0c96aa..77fabdee9 100644 --- a/ext/ply/test/lex_token5.py +++ b/ext/ply/test/lex_token5.py @@ -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() diff --git a/ext/ply/test/rununit.py b/ext/ply/test/rununit.py new file mode 100644 index 000000000..cb7a2298b --- /dev/null +++ b/ext/ply/test/rununit.py @@ -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() + diff --git a/ext/ply/test/yacc_badargs.exp b/ext/ply/test/yacc_badargs.exp index b145c51f2..e99467659 100644 --- a/ext/ply/test/yacc_badargs.exp +++ b/ext/ply/test/yacc_badargs.exp @@ -1,3 +1,3 @@ -./yacc_badargs.py:21: Rule 'p_statement_assign' has too many arguments. -./yacc_badargs.py:25: Rule 'p_statement_expr' requires an argument. -yacc.YaccError: Unable to construct parser. +./yacc_badargs.py:23: Rule 'p_statement_assign' has too many arguments. +./yacc_badargs.py:27: Rule 'p_statement_expr' requires an argument. +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_badargs.py b/ext/ply/test/yacc_badargs.py index 12075efcc..810e5298a 100644 --- a/ext/ply/test/yacc_badargs.py +++ b/ext/ply/test/yacc_badargs.py @@ -5,6 +5,8 @@ # ----------------------------------------------------------------------------- import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc from calclex import tokens @@ -59,7 +61,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_badprec.exp b/ext/ply/test/yacc_badprec.exp index 7764b0246..f4f574b99 100644 --- a/ext/ply/test/yacc_badprec.exp +++ b/ext/ply/test/yacc_badprec.exp @@ -1 +1 @@ -yacc.YaccError: precedence must be a list or tuple. +ply.yacc.YaccError: precedence must be a list or tuple. diff --git a/ext/ply/test/yacc_badprec.py b/ext/ply/test/yacc_badprec.py index 55bf7720d..8f64652e6 100644 --- a/ext/ply/test/yacc_badprec.py +++ b/ext/ply/test/yacc_badprec.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -55,7 +58,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_badprec2.exp b/ext/ply/test/yacc_badprec2.exp index 1df1427b2..8fac075ce 100644 --- a/ext/ply/test/yacc_badprec2.exp +++ b/ext/ply/test/yacc_badprec2.exp @@ -1,3 +1,3 @@ yacc: Invalid precedence table. -yacc: Generating SLR parsing table... -yacc: 4 shift/reduce conflicts +yacc: Generating LALR parsing table... +yacc: 8 shift/reduce conflicts diff --git a/ext/ply/test/yacc_badprec2.py b/ext/ply/test/yacc_badprec2.py index 9cbc99827..206bda768 100644 --- a/ext/ply/test/yacc_badprec2.py +++ b/ext/ply/test/yacc_badprec2.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_badrule.exp b/ext/ply/test/yacc_badrule.exp index 553779778..a87bf7d68 100644 --- a/ext/ply/test/yacc_badrule.exp +++ b/ext/ply/test/yacc_badrule.exp @@ -1,5 +1,5 @@ -./yacc_badrule.py:22: Syntax error. Expected ':' -./yacc_badrule.py:26: Syntax error in rule 'statement' -./yacc_badrule.py:31: Syntax error. Expected ':' -./yacc_badrule.py:40: Syntax error. Expected ':' -yacc.YaccError: Unable to construct parser. +./yacc_badrule.py:25: Syntax error. Expected ':' +./yacc_badrule.py:29: Syntax error in rule 'statement' +./yacc_badrule.py:34: Syntax error. Expected ':' +./yacc_badrule.py:43: Syntax error. Expected ':' +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_badrule.py b/ext/ply/test/yacc_badrule.py index cad3a967e..f5fef8ad6 100644 --- a/ext/ply/test/yacc_badrule.py +++ b/ext/ply/test/yacc_badrule.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_badtok.exp b/ext/ply/test/yacc_badtok.exp index f6e64726c..ccdc0e7a1 100644 --- a/ext/ply/test/yacc_badtok.exp +++ b/ext/ply/test/yacc_badtok.exp @@ -1 +1 @@ -yacc.YaccError: tokens must be a list or tuple. +ply.yacc.YaccError: tokens must be a list or tuple. diff --git a/ext/ply/test/yacc_badtok.py b/ext/ply/test/yacc_badtok.py index a17d26aaa..4f2af5162 100644 --- a/ext/ply/test/yacc_badtok.py +++ b/ext/ply/test/yacc_badtok.py @@ -7,6 +7,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + tokens = "Hello" # Parsing rules @@ -60,7 +63,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_dup.exp b/ext/ply/test/yacc_dup.exp index 99f3fe22c..fdfb2103d 100644 --- a/ext/ply/test/yacc_dup.exp +++ b/ext/ply/test/yacc_dup.exp @@ -1,4 +1,4 @@ -./yacc_dup.py:25: Function p_statement redefined. Previously defined on line 21 +./yacc_dup.py:28: Function p_statement redefined. Previously defined on line 24 yacc: Warning. Token 'EQUALS' defined, but not used. yacc: Warning. There is 1 unused token. -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... diff --git a/ext/ply/test/yacc_dup.py b/ext/ply/test/yacc_dup.py index 557cd0ae1..e0b683d8f 100644 --- a/ext/ply/test/yacc_dup.py +++ b/ext/ply/test/yacc_dup.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_error1.exp b/ext/ply/test/yacc_error1.exp index 980fc905c..13bed0461 100644 --- a/ext/ply/test/yacc_error1.exp +++ b/ext/ply/test/yacc_error1.exp @@ -1 +1 @@ -yacc.YaccError: ./yacc_error1.py:59: p_error() requires 1 argument. +ply.yacc.YaccError: ./yacc_error1.py:62: p_error() requires 1 argument. diff --git a/ext/ply/test/yacc_error1.py b/ext/ply/test/yacc_error1.py index 413004520..2768fc14a 100644 --- a/ext/ply/test/yacc_error1.py +++ b/ext/ply/test/yacc_error1.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t,s): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_error2.exp b/ext/ply/test/yacc_error2.exp index d0573b4dd..4a7628d78 100644 --- a/ext/ply/test/yacc_error2.exp +++ b/ext/ply/test/yacc_error2.exp @@ -1 +1 @@ -yacc.YaccError: ./yacc_error2.py:59: p_error() requires 1 argument. +ply.yacc.YaccError: ./yacc_error2.py:62: p_error() requires 1 argument. diff --git a/ext/ply/test/yacc_error2.py b/ext/ply/test/yacc_error2.py index d4fd1d219..8f3a05290 100644 --- a/ext/ply/test/yacc_error2.py +++ b/ext/ply/test/yacc_error2.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_error3.exp b/ext/ply/test/yacc_error3.exp index 31eaee754..7fca2fe95 100644 --- a/ext/ply/test/yacc_error3.exp +++ b/ext/ply/test/yacc_error3.exp @@ -1 +1 @@ -yacc.YaccError: 'p_error' defined, but is not a function. +ply.yacc.YaccError: 'p_error' defined, but is not a function or method. diff --git a/ext/ply/test/yacc_error3.py b/ext/ply/test/yacc_error3.py index 7093fab48..b387de5d1 100644 --- a/ext/ply/test/yacc_error3.py +++ b/ext/ply/test/yacc_error3.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -58,7 +61,6 @@ def p_expression_name(t): p_error = "blah" -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_inf.exp b/ext/ply/test/yacc_inf.exp index a7f47dada..88cfa4a2e 100644 --- a/ext/ply/test/yacc_inf.exp +++ b/ext/ply/test/yacc_inf.exp @@ -2,4 +2,4 @@ yacc: Warning. Token 'NUMBER' defined, but not used. yacc: Warning. There is 1 unused token. yacc: Infinite recursion detected for symbol 'statement'. yacc: Infinite recursion detected for symbol 'expression'. -yacc.YaccError: Unable to construct parser. +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_inf.py b/ext/ply/test/yacc_inf.py index 885e2c4df..9b9aef75d 100644 --- a/ext/ply/test/yacc_inf.py +++ b/ext/ply/test/yacc_inf.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -47,7 +50,6 @@ def p_expression_group(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_missing1.exp b/ext/ply/test/yacc_missing1.exp index 065d6a54a..de63d4f48 100644 --- a/ext/ply/test/yacc_missing1.exp +++ b/ext/ply/test/yacc_missing1.exp @@ -1,2 +1,2 @@ -./yacc_missing1.py:22: Symbol 'location' used, but not defined as a token or a rule. -yacc.YaccError: Unable to construct parser. +./yacc_missing1.py:25: Symbol 'location' used, but not defined as a token or a rule. +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_missing1.py b/ext/ply/test/yacc_missing1.py index e63904d0e..fbc54d8c5 100644 --- a/ext/ply/test/yacc_missing1.py +++ b/ext/ply/test/yacc_missing1.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_nodoc.exp b/ext/ply/test/yacc_nodoc.exp index 3f52a3287..889ccfce7 100644 --- a/ext/ply/test/yacc_nodoc.exp +++ b/ext/ply/test/yacc_nodoc.exp @@ -1,2 +1,2 @@ -./yacc_nodoc.py:25: No documentation string specified in function 'p_statement_expr' -yacc: Generating SLR parsing table... +./yacc_nodoc.py:28: No documentation string specified in function 'p_statement_expr' +yacc: Generating LALR parsing table... diff --git a/ext/ply/test/yacc_nodoc.py b/ext/ply/test/yacc_nodoc.py index e3941bdaa..4c5ab20a9 100644 --- a/ext/ply/test/yacc_nodoc.py +++ b/ext/ply/test/yacc_nodoc.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -58,7 +61,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_noerror.exp b/ext/ply/test/yacc_noerror.exp index 986fa31fa..3ae771225 100644 --- a/ext/ply/test/yacc_noerror.exp +++ b/ext/ply/test/yacc_noerror.exp @@ -1,2 +1,2 @@ yacc: Warning. no p_error() function is defined. -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... diff --git a/ext/ply/test/yacc_noerror.py b/ext/ply/test/yacc_noerror.py index d92f48ea6..9c11838eb 100644 --- a/ext/ply/test/yacc_noerror.py +++ b/ext/ply/test/yacc_noerror.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -56,7 +59,7 @@ def p_expression_name(t): print "Undefined name '%s'" % t[1] t[0] = 0 -import yacc + yacc.yacc() diff --git a/ext/ply/test/yacc_nop.exp b/ext/ply/test/yacc_nop.exp index 062878b9e..515fff7dc 100644 --- a/ext/ply/test/yacc_nop.exp +++ b/ext/ply/test/yacc_nop.exp @@ -1,2 +1,2 @@ -./yacc_nop.py:25: Warning. Possible grammar rule 'statement_expr' defined without p_ prefix. -yacc: Generating SLR parsing table... +./yacc_nop.py:28: Warning. Possible grammar rule 'statement_expr' defined without p_ prefix. +yacc: Generating LALR parsing table... diff --git a/ext/ply/test/yacc_nop.py b/ext/ply/test/yacc_nop.py index c599ffd5d..c0b431d4b 100644 --- a/ext/ply/test/yacc_nop.py +++ b/ext/ply/test/yacc_nop.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_notfunc.exp b/ext/ply/test/yacc_notfunc.exp index 271167341..f73bc93a5 100644 --- a/ext/ply/test/yacc_notfunc.exp +++ b/ext/ply/test/yacc_notfunc.exp @@ -1,4 +1,4 @@ yacc: Warning. 'p_statement_assign' not defined as a function yacc: Warning. Token 'EQUALS' defined, but not used. yacc: Warning. There is 1 unused token. -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... diff --git a/ext/ply/test/yacc_notfunc.py b/ext/ply/test/yacc_notfunc.py index f61663d60..838935509 100644 --- a/ext/ply/test/yacc_notfunc.py +++ b/ext/ply/test/yacc_notfunc.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -57,7 +60,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_notok.exp b/ext/ply/test/yacc_notok.exp index 708f6f597..d2399fe17 100644 --- a/ext/ply/test/yacc_notok.exp +++ b/ext/ply/test/yacc_notok.exp @@ -1 +1 @@ -yacc.YaccError: module does not define a list 'tokens' +ply.yacc.YaccError: module does not define a list 'tokens' diff --git a/ext/ply/test/yacc_notok.py b/ext/ply/test/yacc_notok.py index dfa0059be..e566a1bf4 100644 --- a/ext/ply/test/yacc_notok.py +++ b/ext/ply/test/yacc_notok.py @@ -7,6 +7,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + # Parsing rules precedence = ( ('left','PLUS','MINUS'), @@ -58,7 +61,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_rr.exp b/ext/ply/test/yacc_rr.exp index 0ec556d16..f73cefdec 100644 --- a/ext/ply/test/yacc_rr.exp +++ b/ext/ply/test/yacc_rr.exp @@ -1,2 +1,2 @@ -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... yacc: 1 reduce/reduce conflict diff --git a/ext/ply/test/yacc_rr.py b/ext/ply/test/yacc_rr.py index c061c2c17..bb8cba235 100644 --- a/ext/ply/test/yacc_rr.py +++ b/ext/ply/test/yacc_rr.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -63,7 +66,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_simple.exp b/ext/ply/test/yacc_simple.exp index de7964b6f..38360315f 100644 --- a/ext/ply/test/yacc_simple.exp +++ b/ext/ply/test/yacc_simple.exp @@ -1 +1 @@ -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... diff --git a/ext/ply/test/yacc_simple.py b/ext/ply/test/yacc_simple.py index 7b4b40b17..b5dc9f39c 100644 --- a/ext/ply/test/yacc_simple.py +++ b/ext/ply/test/yacc_simple.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_sr.exp b/ext/ply/test/yacc_sr.exp index 7225ad94b..1b764502c 100644 --- a/ext/ply/test/yacc_sr.exp +++ b/ext/ply/test/yacc_sr.exp @@ -1,2 +1,2 @@ -yacc: Generating SLR parsing table... +yacc: Generating LALR parsing table... yacc: 20 shift/reduce conflicts diff --git a/ext/ply/test/yacc_sr.py b/ext/ply/test/yacc_sr.py index 4341f6997..e2f03ec74 100644 --- a/ext/ply/test/yacc_sr.py +++ b/ext/ply/test/yacc_sr.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -54,7 +57,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_term1.exp b/ext/ply/test/yacc_term1.exp index 422d2bacd..40f9bdf64 100644 --- a/ext/ply/test/yacc_term1.exp +++ b/ext/ply/test/yacc_term1.exp @@ -1,2 +1,2 @@ -./yacc_term1.py:22: Illegal rule name 'NUMBER'. Already defined as a token. -yacc.YaccError: Unable to construct parser. +./yacc_term1.py:25: Illegal rule name 'NUMBER'. Already defined as a token. +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_term1.py b/ext/ply/test/yacc_term1.py index 97a2e7a60..bbc52da86 100644 --- a/ext/ply/test/yacc_term1.py +++ b/ext/ply/test/yacc_term1.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -59,7 +62,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_unused.exp b/ext/ply/test/yacc_unused.exp index 390754de3..6caafd266 100644 --- a/ext/ply/test/yacc_unused.exp +++ b/ext/ply/test/yacc_unused.exp @@ -1,4 +1,4 @@ -./yacc_unused.py:60: Symbol 'COMMA' used, but not defined as a token or a rule. +./yacc_unused.py:63: Symbol 'COMMA' used, but not defined as a token or a rule. yacc: Symbol 'COMMA' is unreachable. yacc: Symbol 'exprlist' is unreachable. -yacc.YaccError: Unable to construct parser. +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_unused.py b/ext/ply/test/yacc_unused.py index 4cbd63327..3a61f99cd 100644 --- a/ext/ply/test/yacc_unused.py +++ b/ext/ply/test/yacc_unused.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -68,7 +71,6 @@ def p_expr_list_2(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() diff --git a/ext/ply/test/yacc_uprec.exp b/ext/ply/test/yacc_uprec.exp index b1a71a250..eb9a39886 100644 --- a/ext/ply/test/yacc_uprec.exp +++ b/ext/ply/test/yacc_uprec.exp @@ -1,2 +1,2 @@ -./yacc_uprec.py:35: Nothing known about the precedence of 'UMINUS' -yacc.YaccError: Unable to construct parser. +./yacc_uprec.py:38: Nothing known about the precedence of 'UMINUS' +ply.yacc.YaccError: Unable to construct parser. diff --git a/ext/ply/test/yacc_uprec.py b/ext/ply/test/yacc_uprec.py index 139ce6318..0e8711e88 100644 --- a/ext/ply/test/yacc_uprec.py +++ b/ext/ply/test/yacc_uprec.py @@ -6,6 +6,9 @@ import sys sys.tracebacklimit = 0 +sys.path.insert(0,"..") +import ply.yacc as yacc + from calclex import tokens # Parsing rules @@ -54,7 +57,6 @@ def p_expression_name(t): def p_error(t): print "Syntax error at '%s'" % t.value -import yacc yacc.yacc() |