diff options
Diffstat (limited to 'chall/ply-2.2/doc')
| -rw-r--r-- | chall/ply-2.2/doc/makedoc.py | 194 | ||||
| -rw-r--r-- | chall/ply-2.2/doc/ply.html | 2874 |
2 files changed, 3068 insertions, 0 deletions
diff --git a/chall/ply-2.2/doc/makedoc.py b/chall/ply-2.2/doc/makedoc.py new file mode 100644 index 0000000..415a53a --- /dev/null +++ b/chall/ply-2.2/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/chall/ply-2.2/doc/ply.html b/chall/ply-2.2/doc/ply.html new file mode 100644 index 0000000..b3219ea --- /dev/null +++ b/chall/ply-2.2/doc/ply.html @@ -0,0 +1,2874 @@ +<html> +<head> +<title>PLY (Python Lex-Yacc)</title> +</head> +<body bgcolor="#ffffff"> + +<h1>PLY (Python Lex-Yacc)</h1> + +<b> +David M. Beazley <br> +dave@dabeaz.com<br> +</b> + +<p> +<b>PLY Version: 2.2</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><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 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 influenced by common +usability problems encountered by students. + +<p> +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.). 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 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> + + +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. <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, +<tt>lex.py</tt> provides an external interface in the form of a +<tt>token()</tt> function that returns the next valid token on the +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. + +<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. In fact, everything that is possible in traditional yacc +should be supported in PLY. + +<p> +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> + +A tokenizer splits the string into individual tokens + +<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> +# ------------------------------------------------------------ +# calclex.py +# +# tokenizer for a simple expression evaluator for +# numbers and +,-,*,/ +# ------------------------------------------------------------ +import ply.lex as lex + +# 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) + +# 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 + + -20 *2 +''' + +# Give the lexer some input +lex.input(data) + +# Tokenize +while 1: + tok = lex.token() + if not tok: break # No more input + print tok +</pre> +</blockquote> + +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): + +<blockquote> +<pre> +t_PLUS = r'\+' +</pre> +</blockquote> + +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, this rule matches numbers and +converts the string into a Python integer. + +<blockquote> +<pre> +def t_NUMBER(t): + r'\d+' + try: + t.value = int(t.value) + except ValueError: + print "Number %s is too large!" % t.value + t.value = 0 + return t +</pre> +</blockquote> + +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 (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> +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 +that should be completely ignored in the input stream. +Usually this is used to skip over whitespace and other non-essential characters. +Although it is possible to define a regular expression rule for whitespace in a manner +similar to <tt>t_newline()</tt>, the use of <tt>t_ignore</tt> provides substantially better +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, 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 +uses Python reflection (or introspection) to read the the regular expression rules +out of the calling context and build the lexer. Once the lexer has been built, two functions can +be used to control the lexer. + +<ul> +<li><tt>lex.input(data)</tt>. Reset the lexer and store a new input string. +<li><tt>lex.token()</tt>. Return the next token. Returns a special <tt>LexToken</tt> instance on success or +None if the end of the input text has been reached. +</ul> + +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> +lexer = lex.lex() +lexer.input(sometext) +while 1: + tok = lexer.token() + if not tok: break + print tok +</pre> +</blockquote> + +<p> +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> +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. + +<H3><a name="ply_nn14"></a>3.11 The @TOKEN decorator</H3> + + +In some applications, you may want to define build tokens from as a series of +more complex regular expression rules. For example: + +<blockquote> +<pre> +digit = r'([0-9])' +nondigit = r'([_A-Za-z])' +identifier = r'(' + nondigit + r'(' + digit + r'|' + nondigit + r')*)' + +def t_ID(t): + # want docstring to be identifier above. ????? + ... +</pre> +</blockquote> + +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): + ... +</pre> +</blockquote> + +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): + ... + +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> + +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> +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> +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.num_count = 0 # Set the initial count +</pre> +</blockquote> + +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> +If necessary, a lexer object can be quickly duplicated by invoking its <tt>clone()</tt> method. For example: + +<blockquote> +<pre> +lexer = lex.lex() +... +newlexer = lexer.clone() +</pre> +</blockquote> + +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> +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> +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> +<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> +states = ( + ('foo','exclusive'), + ('bar','inclusive'), +) +</pre> +</blockquote> + +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. 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. + +<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><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, <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: + +<blockquote> +<pre> +expression : expression + term + | expression - term + | term + +term : term * factor + | term / factor + | factor + +factor : NUMBER + | ( expression ) +</pre> +</blockquote> + +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 +recognized, the action describes what to do. For example, given the +expression grammar above, you might write the specification for a +simple calculator like this: + +<blockquote> +<pre> +Grammar Action +-------------------------------- -------------------------------------------- +expression0 : expression1 + term expression0.val = expression1.val + term.val + | expression1 - term expression0.val = expression1.val - term.val + | term expression0.val = term.val + +term0 : term1 * factor term0.val = term1.val * factor.val + | term1 / factor term0.val = term1.val / factor.val + | factor term0.val = factor.val + +factor : NUMBER factor.val = int(NUMBER.lexval) + | ( expression ) factor.val = expression.val +</pre> +</blockquote> + +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. + +<p> +LR parsing is commonly implemented by shifting grammar symbols onto a stack and looking at the stack and the next +input token for patterns. The details of the algorithm can be found in a compiler text, but the +following example illustrates the steps that are performed if you wanted to parse the expression +<tt>3 + 5 * (10 - 20)</tt> using the grammar defined above: + +<blockquote> +<pre> +Step Symbol Stack Input Tokens Action +---- --------------------- --------------------- ------------------------------- +1 $ 3 + 5 * ( 10 - 20 )$ Shift 3 +2 $ 3 + 5 * ( 10 - 20 )$ Reduce factor : NUMBER +3 $ factor + 5 * ( 10 - 20 )$ Reduce term : factor +4 $ term + 5 * ( 10 - 20 )$ Reduce expr : term +5 $ expr + 5 * ( 10 - 20 )$ Shift + +6 $ expr + 5 * ( 10 - 20 )$ Shift 5 +7 $ expr + 5 * ( 10 - 20 )$ Reduce factor : NUMBER +8 $ expr + factor * ( 10 - 20 )$ Reduce term : factor +9 $ expr + term * ( 10 - 20 )$ Shift * +10 $ expr + term * ( 10 - 20 )$ Shift ( +11 $ expr + term * ( 10 - 20 )$ Shift 10 +12 $ expr + term * ( 10 - 20 )$ Reduce factor : NUMBER +13 $ expr + term * ( factor - 20 )$ Reduce term : factor +14 $ expr + term * ( term - 20 )$ Reduce expr : term +15 $ expr + term * ( expr - 20 )$ Shift - +16 $ expr + term * ( expr - 20 )$ Shift 20 +17 $ expr + term * ( expr - 20 )$ Reduce factor : NUMBER +18 $ expr + term * ( expr - factor )$ Reduce term : factor +19 $ expr + term * ( expr - term )$ Reduce expr : expr - term +20 $ expr + term * ( expr )$ Shift ) +21 $ expr + term * ( expr ) $ Reduce factor : (expr) +22 $ expr + term * factor $ Reduce term : term * factor +23 $ expr + term $ Reduce expr : expr + term +24 $ expr $ Reduce expr +25 $ $ Success! +</pre> +</blockquote> + +When parsing the expression, an underlying state machine and the current input token determine what to do next. +If the next token looks like part of a valid grammar rule (based on other items on the stack), it is generally shifted +onto the stack. If the top of the stack contains a valid right-hand-side of a grammar rule, it is +usually "reduced" and the symbols replaced with the symbol on the left-hand-side. When this reduction occurs, the +appropriate action is triggered (if defined). If the input token can't be shifted and the top of stack doesn't match +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 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><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>: + +<blockquote> +<pre> +# Yacc example + +import ply.yacc as yacc + +# Get the token map from the lexer. This is required. +from calclex import tokens + +def p_expression_plus(p): + 'expression : expression PLUS term' + p[0] = p[1] + p[3] + +def p_expression_minus(p): + 'expression : expression MINUS term' + p[0] = p[1] - p[3] + +def p_expression_term(p): + 'expression : term' + p[0] = p[1] + +def p_term_times(p): + 'term : term TIMES factor' + p[0] = p[1] * p[3] + +def p_term_div(p): + 'term : term DIVIDE factor' + p[0] = p[1] / p[3] + +def p_term_factor(p): + 'term : factor' + p[0] = p[1] + +def p_factor_num(p): + 'factor : NUMBER' + p[0] = p[1] + +def p_factor_expr(p): + 'factor : LPAREN expression RPAREN' + p[0] = p[2] + +# Error rule for syntax errors +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 > ') + except EOFError: + break + if not s: continue + result = yacc.parse(s) + print result +</pre> +</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. 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(p): + 'expression : expression PLUS term' + # ^ ^ ^ ^ + # p[0] p[1] p[2] p[3] + + p[0] = p[1] + p[3] +</pre> +</blockquote> + +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>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>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(p)</tt> rule is defined to catch syntax errors. See the error handling section +below for more detail. + +<p> +To build the parser, call the <tt>yacc.yacc()</tt> function. This function +looks at the module and attempts to construct all of the LR parsing tables for the grammar +you have specified. The first time <tt>yacc.yacc()</tt> is invoked, you will get a message +such as this: + +<blockquote> +<pre> +$ python calcparse.py +yacc: Generating LALR parsing table... +calc > +</pre> +</blockquote> + +Since table construction is relatively expensive (especially for large +grammars), the resulting parsing table is written to the current +directory in a file called <tt>parsetab.py</tt>. In addition, a +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). 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 +diagnostic messages and possibly raise an exception. Some of the errors that can be detected include: + +<ul> +<li>Duplicated function names (if more than one rule function have the same name in the grammar file). +<li>Shift/reduce and reduce/reduce conflicts generated by ambiguous grammars. +<li>Badly specified grammar rules. +<li>Infinite recursion (rules that can never terminate). +<li>Unused rules and tokens +<li>Undefined rules and tokens +</ul> + +The next few sections now discuss a few finer points of grammar construction. + +<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(p): + 'expression : expression PLUS term' + p[0] = p[1] + p[3] + +def p_expression_minus(t): + 'expression : expression MINUS term' + p[0] = p[1] - p[3] +</pre> +</blockquote> + +Instead of writing two functions, you might write a single function like this: + +<blockquote> +<pre> +def p_expression(p): + '''expression : expression PLUS term + | expression MINUS term''' + if p[2] == '+': + p[0] = p[1] + p[3] + elif p[2] == '-': + p[0] = p[1] - p[3] +</pre> +</blockquote> + +In general, the doc string for any given function can contain multiple grammar rules. So, it would +have also been legal (although possibly confusing) to write this: + +<blockquote> +<pre> +def p_binary_operators(p): + '''expression : expression PLUS term + | expression MINUS term + term : term TIMES factor + | term DIVIDE 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> + +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. 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> + + +<tt>yacc.py</tt> can handle empty productions by defining a rule like this: + +<blockquote> +<pre> +def p_empty(p): + 'empty :' + pass +</pre> +</blockquote> + +Now to use the empty production, simply use 'empty' as a symbol. For example: + +<blockquote> +<pre> +def p_optitem(p): + 'optitem : item' + ' | empty' + ... +</pre> +</blockquote> + +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 +much more natural way to express the grammar is in a more compact form like this: + +<blockquote> +<pre> +expression : expression PLUS expression + | expression MINUS expression + | expression TIMES expression + | expression DIVIDE expression + | LPAREN expression RPAREN + | NUMBER +</pre> +</blockquote> + +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 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" +or a "reduce/reduce conflicts". A shift/reduce conflict is caused when the parser generator can't decide +whether or not to reduce a rule or shift a symbol on the parsing stack. For example, consider +the string "3 * 4 + 5" and the internal parsing stack: + +<blockquote> +<pre> +Step Symbol Stack Input Tokens Action +---- --------------------- --------------------- ------------------------------- +1 $ 3 * 4 + 5$ Shift 3 +2 $ 3 * 4 + 5$ Reduce : expression : NUMBER +3 $ expr * 4 + 5$ Shift * +4 $ expr * 4 + 5$ Shift 4 +5 $ expr * 4 + 5$ Reduce: expression : NUMBER +6 $ expr * expr + 5$ SHIFT/REDUCE CONFLICT ???? +</pre> +</blockquote> + +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. + +<p> +By default, all shift/reduce conflicts are resolved in favor of shifting. Therefore, in the above +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 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 +<tt>precedence</tt> to the grammar file like this: + +<blockquote> +<pre> +precedence = ( + ('left', 'PLUS', 'MINUS'), + ('left', 'TIMES', 'DIVIDE'), +) +</pre> +</blockquote> + +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. +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 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> +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> + +When shift/reduce conflicts are encountered, the parser generator resolves the conflict by +looking at the precedence rules and associativity specifiers. + +<p> +<ol> +<li>If the current token has higher precedence, it is shifted. +<li>If the grammar rule on the stack has higher precedence, the rule is reduced. +<li>If the current token and the grammar rule have the same precedence, the +rule is reduced for left associativity, whereas the token is shifted for right associativity. +<li>If nothing is known about the precedence, shift/reduce conflicts are resolved in +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. + +<p> +One problem with the precedence specifier technique is that it is sometimes necessary to +change the precedence of an operator in certain contents. For example, consider a unary-minus operator +in "3 + 4 * -5". Normally, unary minus has a very high precedence--being evaluated before the multiply. +However, in our precedence specifier, MINUS has a lower precedence than TIMES. To deal with this, +precedence rules can be given for fictitious tokens like this: + +<blockquote> +<pre> +precedence = ( + ('left', 'PLUS', 'MINUS'), + ('left', 'TIMES', 'DIVIDE'), + ('right', 'UMINUS'), # Unary minus operator +) +</pre> +</blockquote> + +Now, in the grammar file, we can write our unary minus rule like this: + +<blockquote> +<pre> +def p_expr_uminus(p): + 'expression : MINUS expression %prec UMINUS' + p[0] = -p[2] +</pre> +</blockquote> + +In this case, <tt>%prec UMINUS</tt> overrides the default rule precedence--setting it to that +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 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> +<pre> +precedence = ( + ('nonassoc', 'LESSTHAN', 'GREATERTHAN'), # Nonassociative operators + ('left', 'PLUS', 'MINUS'), + ('left', 'TIMES', 'DIVIDE'), + ('right', 'UMINUS'), # Unary minus operator +) +</pre> +</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 +rule that appears first in the grammar file. Reduce/reduce conflicts +are almost always caused when different sets of grammar rules somehow +generate the same set of symbols. For example: + +<blockquote> +<pre> +assignment : ID EQUALS NUMBER + | ID EQUALS expression + +expression : expression PLUS expression + | expression MINUS expression + | expression TIMES expression + | expression DIVIDE expression + | LPAREN expression RPAREN + | NUMBER +</pre> +</blockquote> + +In this case, a reduce/reduce conflict exists between these two rules: + +<blockquote> +<pre> +assignment : ID EQUALS NUMBER +expression : NUMBER +</pre> +</blockquote> + +For example, if you wrote "a = 5", the parser can't figure out if this +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>. + +<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 +'parser.out' when it generates the parsing table. The contents of this file look like the following: + +<blockquote> +<pre> +Unused terminals: + + +Grammar + +Rule 1 expression -> expression PLUS expression +Rule 2 expression -> expression MINUS expression +Rule 3 expression -> expression TIMES expression +Rule 4 expression -> expression DIVIDE expression +Rule 5 expression -> NUMBER +Rule 6 expression -> LPAREN expression RPAREN + +Terminals, with rules where they appear + +TIMES : 3 +error : +MINUS : 2 +RPAREN : 6 +LPAREN : 6 +DIVIDE : 4 +PLUS : 1 +NUMBER : 5 + +Nonterminals, with rules where they appear + +expression : 1 1 2 2 3 3 4 4 6 0 + + +Parsing method: LALR + + +state 0 + + S' -> . expression + expression -> . expression PLUS expression + expression -> . expression MINUS expression + expression -> . expression TIMES expression + expression -> . expression DIVIDE expression + expression -> . NUMBER + expression -> . LPAREN expression RPAREN + + NUMBER shift and go to state 3 + LPAREN shift and go to state 2 + + +state 1 + + S' -> expression . + expression -> expression . PLUS expression + expression -> expression . MINUS expression + expression -> expression . TIMES expression + expression -> expression . DIVIDE expression + + PLUS shift and go to state 6 + MINUS shift and go to state 5 + TIMES shift and go to state 4 + DIVIDE shift and go to state 7 + + +state 2 + + expression -> LPAREN . expression RPAREN + expression -> . expression PLUS expression + expression -> . expression MINUS expression + expression -> . expression TIMES expression + expression -> . expression DIVIDE expression + expression -> . NUMBER + expression -> . LPAREN expression RPAREN + + NUMBER shift and go to state 3 + LPAREN shift and go to state 2 + + +state 3 + + expression -> NUMBER . + + $ reduce using rule 5 + PLUS reduce using rule 5 + MINUS reduce using rule 5 + TIMES reduce using rule 5 + DIVIDE reduce using rule 5 + RPAREN reduce using rule 5 + + +state 4 + + expression -> expression TIMES . expression + expression -> . expression PLUS expression + expression -> . expression MINUS expression + expression -> . expression TIMES expression + expression -> . expression DIVIDE expression + expression -> . NUMBER + expression -> . LPAREN expression RPAREN + + NUMBER shift and go to state 3 + LPAREN shift and go to state 2 + + +state 5 + + expression -> expression MINUS . expression + expression -> . expression PLUS expression + expression -> . expression MINUS expression + expression -> . expression TIMES expression + expression -> . expression DIVIDE expression + expression -> . NUMBER + expression -> . LPAREN expression RPAREN + + NUMBER shift and go to state 3 + LPAREN shift and go to state 2 + + +state 6 + + expression -> expression PLUS . expression + expression -> . expression PLUS expression + expression -> . expression MINUS expression + expression -> . expression TIMES expression + expression -> . expression DIVIDE expression + expression -> . NUMBER + expression -> . LPAREN expression RPAREN + + NUMBER shift and go to state 3 + LPAREN shift and go to state 2 + + +state 7 + + expression -> expression DIVIDE . expression + expression -> . expression PLUS expression + expression -> . expression MINUS expression + expression -> . expression TIMES expression + expression -> . expression DIVIDE expression + expression -> . NUMBER + expression -> . LPAREN expression RPAREN + + NUMBER shift and go to state 3 + LPAREN shift and go to state 2 + + +state 8 + + expression -> LPAREN expression . RPAREN + expression -> expression . PLUS expression + expression -> expression . MINUS expression + expression -> expression . TIMES expression + expression -> expression . DIVIDE expression + + RPAREN shift and go to state 13 + PLUS shift and go to state 6 + MINUS shift and go to state 5 + TIMES shift and go to state 4 + DIVIDE shift and go to state 7 + + +state 9 + + expression -> expression TIMES expression . + expression -> expression . PLUS expression + expression -> expression . MINUS expression + expression -> expression . TIMES expression + expression -> expression . DIVIDE expression + + $ reduce using rule 3 + PLUS reduce using rule 3 + MINUS reduce using rule 3 + TIMES reduce using rule 3 + DIVIDE reduce using rule 3 + RPAREN reduce using rule 3 + + ! PLUS [ shift and go to state 6 ] + ! MINUS [ shift and go to state 5 ] + ! TIMES [ shift and go to state 4 ] + ! DIVIDE [ shift and go to state 7 ] + +state 10 + + expression -> expression MINUS expression . + expression -> expression . PLUS expression + expression -> expression . MINUS expression + expression -> expression . TIMES expression + expression -> expression . DIVIDE expression + + $ reduce using rule 2 + PLUS reduce using rule 2 + MINUS reduce using rule 2 + RPAREN reduce using rule 2 + TIMES shift and go to state 4 + DIVIDE shift and go to state 7 + + ! TIMES [ reduce using rule 2 ] + ! DIVIDE [ reduce using rule 2 ] + ! PLUS [ shift and go to state 6 ] + ! MINUS [ shift and go to state 5 ] + +state 11 + + expression -> expression PLUS expression . + expression -> expression . PLUS expression + expression -> expression . MINUS expression + expression -> expression . TIMES expression + expression -> expression . DIVIDE expression + + $ reduce using rule 1 + PLUS reduce using rule 1 + MINUS reduce using rule 1 + RPAREN reduce using rule 1 + TIMES shift and go to state 4 + DIVIDE shift and go to state 7 + + ! TIMES [ reduce using rule 1 ] + ! DIVIDE [ reduce using rule 1 ] + ! PLUS [ shift and go to state 6 ] + ! MINUS [ shift and go to state 5 ] + +state 12 + + expression -> expression DIVIDE expression . + expression -> expression . PLUS expression + expression -> expression . MINUS expression + expression -> expression . TIMES expression + expression -> expression . DIVIDE expression + + $ reduce using rule 4 + PLUS reduce using rule 4 + MINUS reduce using rule 4 + TIMES reduce using rule 4 + DIVIDE reduce using rule 4 + RPAREN reduce using rule 4 + + ! PLUS [ shift and go to state 6 ] + ! MINUS [ shift and go to state 5 ] + ! TIMES [ shift and go to state 4 ] + ! DIVIDE [ shift and go to state 7 ] + +state 13 + + expression -> LPAREN expression RPAREN . + + $ reduce using rule 6 + PLUS reduce using rule 6 + MINUS reduce using rule 6 + TIMES reduce using rule 6 + DIVIDE reduce using rule 6 + RPAREN reduce using rule 6 +</pre> +</blockquote> + +In the file, each state of the grammar is described. Within each state the "." indicates the current +location of the parse within any applicable grammar rules. In addition, the actions for each valid +input token are listed. When a shift/reduce or reduce/reduce conflict arises, rules <em>not</em> selected +are prefixed with an !. For example: + +<blockquote> +<pre> + ! TIMES [ reduce using rule 2 ] + ! DIVIDE [ reduce using rule 2 ] + ! PLUS [ shift and go to state 6 ] + ! MINUS [ shift and go to state 5 ] +</pre> +</blockquote> + +By looking at these rules (and with a little practice), you can usually track down the source +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>. + +<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 +source of the error). Error recovery in LR parsers is a delicate +topic that involves ancient rituals and black-magic. The recovery mechanism +provided by <tt>yacc.py</tt> is comparable to Unix yacc so you may want +consult a book like O'Reilly's "Lex and Yacc" for some of the finer details. + +<p> +When a syntax error occurs, <tt>yacc.py</tt> performs the following steps: + +<ol> +<li>On the first occurrence of an error, the user-defined <tt>p_error()</tt> function +is called with the offending token as an argument. Afterwards, the parser enters +an "error-recovery" mode in which it will not make future calls to <tt>p_error()</tt> until it +has successfully shifted at least 3 tokens onto the parsing stack. + +<p> +<li>If no recovery action is taken in <tt>p_error()</tt>, the offending lookahead token is replaced +with a special <tt>error</tt> token. + +<p> +<li>If the offending lookahead token is already set to <tt>error</tt>, the top item of the parsing stack is +deleted. + +<p> +<li>If the entire parsing stack is unwound, the parser enters a restart state and attempts to start +parsing from its initial state. + +<p> +<li>If a grammar rule accepts <tt>error</tt> as a token, it will be +shifted onto the parsing stack. + +<p> +<li>If the top item of the parsing stack is <tt>error</tt>, lookahead tokens will be discarded until the +parser can successfully shift a new symbol or reduce a rule involving <tt>error</tt>. +</ol> + +<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(p): + 'statement : PRINT expr SEMI' + ... +</pre> +</blockquote> + +To account for the possibility of a bad expression, you might write an additional grammar rule like this: + +<blockquote> +<pre> +def p_statement_print_error(p): + 'statement : PRINT error SEMI' + print "Syntax error in print statement. Bad expression" + +</pre> +</blockquote> + +In this case, the <tt>error</tt> token will match any sequence of +tokens that might appear up to the first semicolon that is +encountered. Once the semicolon is reached, the rule will be +invoked and the <tt>error</tt> token will go away. + +<p> +This type of recovery is sometimes known as parser resynchronization. +The <tt>error</tt> token acts as a wildcard for any bad input text and +the token immediately following <tt>error</tt> acts as a +synchronization token. + +<p> +It is important to note that the <tt>error</tt> token usually does not appear as the last token +on the right in an error rule. For example: + +<blockquote> +<pre> +def p_statement_print_error(p): + 'statement : PRINT error' + print "Syntax error in print statement. Bad expression" +</pre> +</blockquote> + +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><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. + +<p> +Panic mode recovery is implemented entirely in the <tt>p_error()</tt> function. For example, this +function starts discarding tokens until it reaches a closing '}'. Then, it restarts the +parser in its initial state. + +<blockquote> +<pre> +def p_error(p): + print "Whoa. You are seriously hosed." + # Read ahead looking for a closing '}' + while 1: + tok = yacc.token() # Get the next token + if not tok or tok.type == 'RBRACE': break + yacc.restart() +</pre> +</blockquote> + +<p> +This function simply discards the bad token and tells the parser that the error was ok. + +<blockquote> +<pre> +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> +</blockquote> + +<P> +Within the <tt>p_error()</tt> function, three functions are available to control the behavior +of the parser: +<p> +<ul> +<li><tt>yacc.errok()</tt>. This resets the parser state so it doesn't think it's in error-recovery +mode. This will prevent an <tt>error</tt> token from being generated and will reset the internal +error counters so that the next syntax error will call <tt>p_error()</tt> again. + +<p> +<li><tt>yacc.token()</tt>. This returns the next token on the input stream. + +<p> +<li><tt>yacc.restart()</tt>. This discards the entire parsing stack and resets the parser +to its initial state. +</ul> + +Note: these functions are only available when invoking <tt>p_error()</tt> and are not available +at any other time. + +<p> +To supply the next lookahead token to the parser, <tt>p_error()</tt> can return a token. This might be +useful if trying to synchronize on special characters. For example: + +<blockquote> +<pre> +def p_error(p): + # Read ahead looking for a terminating ";" + while 1: + tok = yacc.token() # Get the next token + if not tok or tok.type == 'SEMI': break + yacc.errok() + + # Return SEMI to the parser as the next lookahead token + return tok +</pre> +</blockquote> + +<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. + +<H3><a name="ply_nn33"></a>5.9 Line Number and Position Tracking</H3> + + +<tt>yacc.py</tt> automatically tracks line numbers and positions for all of the grammar symbols and tokens it processes. To retrieve the line +numbers, two functions are used in grammar rules: + +<ul> +<li><tt>p.lineno(num)</tt>. Return the starting line number for symbol <em>num</em> +<li><tt>p.linespan(num)</tt>. Return a tuple (startline,endline) with the starting and ending line number 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 = p.linespan(3) # Start,end lines of the right expression + +</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> +To get positional information about where tokens were lexed, the following two functions are used: + +<ul> +<li><tt>p.lexpos(num)</tt>. Return the starting lexing position 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.lexpos(1) # Lexing position of the left expression + p.lexpos(2) # Lexing position of the PLUS operator + p.lexpos(3) # Lexing position of the right expression + ... + start,end = p.lexspan(3) # Start,end positions of the right expression +</pre> +</blockquote> + +Note: The <tt>lexspan()</tt> function only returns the range of values up the start of the last grammar symbol. + +<H3><a name="ply_nn34"></a>5.10 AST Construction</H3> + + +<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>p[0]</tt> in each rule. + +For example: + +<blockquote> +<pre> +class Expr: pass + +class BinOp(Expr): + def __init__(self,left,op,right): + self.type = "binop" + self.left = left + self.right = right + self.op = op + +class Number(Expr): + def __init__(self,value): + self.type = "number" + self.value = value + +def p_expression_binop(p): + '''expression : expression PLUS expression + | expression MINUS expression + | expression TIMES expression + | expression DIVIDE expression''' + + p[0] = BinOp(p[1],p[2],p[3]) + +def p_expression_group(p): + 'expression : LPAREN expression RPAREN' + p[0] = p[2] + +def p_expression_number(p): + 'expression : NUMBER' + p[0] = Number(p[1]) +</pre> +</blockquote> + +To simplify tree traversal, it may make sense to pick a very generic tree structure for your parse tree nodes. +For example: + +<blockquote> +<pre> +class Node: + def __init__(self,type,children=None,leaf=None): + self.type = type + if children: + self.children = children + else: + self.children = [ ] + self.leaf = leaf + +def p_expression_binop(p): + '''expression : expression PLUS expression + | expression MINUS expression + | expression TIMES expression + | expression DIVIDE expression''' + + 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> + +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: + +<blockquote> +<pre> +yacc.parse(lexer=x) +</pre> +</blockquote> +in this case, <tt>x</tt> must be a Lexer object that minimally has a <tt>x.token()</tt> method for retrieving the next +token. If an input string is given to <tt>yacc.parse()</tt>, the lexer must also have an <tt>x.input()</tt> method. + +<p> +<li>By default, the yacc generates tables in debugging mode (which produces the parser.out file and other output). +To disable this, use + +<blockquote> +<pre> +yacc.yacc(debug=0) +</pre> +</blockquote> + +<p> +<li>To change the name of the <tt>parsetab.py</tt> file, use: + +<blockquote> +<pre> +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: + +<blockquote> +<pre> +yacc.parse(debug=1) +</pre> +</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: + +<blockquote> +<pre> +p = yacc.yacc() +... +p.parse() +</pre> +</blockquote> + +Note: The function <tt>yacc.parse()</tt> is bound to the last parser that was generated. + +<p> +<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. + +<p> +It should be noted that table generation is reasonably efficient, even for grammars that involve around a 100 rules +and several hundred states. For more complex languages such as C, table generation may take 30-60 seconds on a slow +machine. Please be patient. + +<p> +<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><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 +behavior of the lexer in some way. + +<p> +To do this, it is important to note that both the lexer and parser are +actually implemented as objects. These objects are returned by the +<tt>lex()</tt> and <tt>yacc()</tt> functions respectively. For example: + +<blockquote> +<pre> +lexer = lex.lex() # Return lexer object +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: + +<blockquote> +<pre> +def t_NUMBER(t): + r'\d+' + ... + print t.lexer # Show lexer object +</pre> +</blockquote> + +In the parser, the "lexer" and "parser" attributes refer to the lexer +and parser objects respectively. + +<blockquote> +<pre> +def p_expr_plus(p): + 'expr : expr PLUS expr' + ... + print p.parser # Show parser object + print p.lexer # Show lexer object +</pre> +</blockquote> + +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><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 +normal mode (i.e., not with the -O or -OO options). However, if you +specify optimized mode like this: + +<blockquote> +<pre> +lex.lex(optimize=1) +yacc.yacc(optimize=1) +</pre> +</blockquote> + +then PLY can later be used when Python runs in optimized mode. To make this work, +make sure you first run Python in normal mode. Once the lexing and parsing tables +have been generated the first time, run Python in optimized mode. PLY will use +the tables without the need for doc strings. + +<p> +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><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. + +</body> +</html> + + + + + + + |