From 8206fb9c4c67341d1da3abb97c0e84a30f07331e Mon Sep 17 00:00:00 2001 From: Guido van Rossum Date: Mon, 26 Aug 1996 00:33:29 +0000 Subject: [PATCH] Final set of changes by Fred before 1.4beta3 --- Demo/parser/Makefile | 6 +- Demo/parser/README | 17 +++ Demo/parser/example.py | 129 +++++++++++++-------- Demo/parser/pprint.py | 87 +++++++------- Demo/parser/simple.py | 1 + Doc/lib/libparser.tex | 252 ++++++++++++++++++++++++++++++++++++----- Doc/libparser.tex | 252 ++++++++++++++++++++++++++++++++++++----- 7 files changed, 589 insertions(+), 155 deletions(-) create mode 100644 Demo/parser/simple.py diff --git a/Demo/parser/Makefile b/Demo/parser/Makefile index 648bf6ed2ac..d71e811e140 100644 --- a/Demo/parser/Makefile +++ b/Demo/parser/Makefile @@ -3,6 +3,10 @@ parser.dvi: parser.tex ../../Doc/libparser.tex # Use a new name for this; the included file uses 'clean' already.... clean-parser: - rm -f *.log *.aux *.dvi *.pyc + rm -f *.log *.aux *.dvi *.pyc *.ps + +dist: + (cd ../..; \ + tar cf - `cat Demo/parser/FILES` | gzip >parsermodule-1.4.tar.gz) include ../../Doc/Makefile diff --git a/Demo/parser/README b/Demo/parser/README index 03696c3c644..3d775aa5bbe 100644 --- a/Demo/parser/README +++ b/Demo/parser/README @@ -4,12 +4,29 @@ to the Python Library Reference for more information. Files: ------ + FILES -- list of files associated with the parser module. + + README -- this file. + example.py -- module that uses the `parser' module to extract information from the parse tree of Python source code. + docstring.py -- sample source file containing only a module docstring. + + simple.py -- sample source containing a "short form" definition. + source.py -- sample source code used to demonstrate ability to handle nested constructs easily using the functions and classes in example.py. + pprint.py -- function to pretty-print Python values. + + test_parser.py program to put the parser module through it's paces. + + parser.tex -- LaTex driver file for formatting the parser module + documentation separately from the library reference. + + Makefile -- `make' rule set to format the parser module manual. + Enjoy! diff --git a/Demo/parser/example.py b/Demo/parser/example.py index c428aff1e82..363f5bb693d 100644 --- a/Demo/parser/example.py +++ b/Demo/parser/example.py @@ -1,6 +1,8 @@ """Simple code to extract class & function docstrings from a module. - +This code is used as an example in the library reference manual in the +section on using the parser module. Refer to the manual for a thorough +discussion of the operation of this code. """ import symbol @@ -23,12 +25,35 @@ def get_docs(fileName): return ModuleInfo(tup, basename) -class DefnInfo: +class SuiteInfoBase: _docstring = '' _name = '' - def __init__(self, tree): - self._name = tree[2][1] + def __init__(self, tree = None): + self._class_info = {} + self._function_info = {} + if tree: + self._extract_info(tree) + + def _extract_info(self, tree): + # extract docstring + if len(tree) == 2: + found, vars = match(DOCSTRING_STMT_PATTERN[1], tree[1]) + else: + found, vars = match(DOCSTRING_STMT_PATTERN, tree[3]) + if found: + self._docstring = eval(vars['docstring']) + # discover inner definitions + for node in tree[1:]: + found, vars = match(COMPOUND_STMT_PATTERN, node) + if found: + cstmt = vars['compound'] + if cstmt[0] == symbol.funcdef: + name = cstmt[2][1] + self._function_info[name] = FunctionInfo(cstmt) + elif cstmt[0] == symbol.classdef: + name = cstmt[2][1] + self._class_info[name] = ClassInfo(cstmt) def get_docstring(self): return self._docstring @@ -36,38 +61,21 @@ class DefnInfo: def get_name(self): return self._name -class SuiteInfoBase(DefnInfo): - def __init__(self): - self._class_info = {} - self._function_info = {} - def get_class_names(self): return self._class_info.keys() def get_class_info(self, name): return self._class_info[name] - def _extract_info(self, tree): - if len(tree) >= 4: - found, vars = match(DOCSTRING_STMT_PATTERN, tree[3]) - if found: - self._docstring = eval(vars['docstring']) - for node in tree[1:]: - if (node[0] == symbol.stmt - and node[1][0] == symbol.compound_stmt): - if node[1][1][0] == symbol.funcdef: - name = node[1][1][2][1] - self._function_info[name] = \ - FunctionInfo(node[1][1]) - elif node[1][1][0] == symbol.classdef: - name = node[1][1][2][1] - self._class_info[name] = ClassInfo(node[1][1]) + def __getitem__(self, name): + try: + return self._class_info[name] + except KeyError: + return self._function_info[name] -class SuiteInfo(SuiteInfoBase): - def __init__(self, tree): - SuiteInfoBase.__init__(self) - self._extract_info(tree) +class SuiteFuncInfo: + # Mixin class providing access to function names and info. def get_function_names(self): return self._function_info.keys() @@ -76,23 +84,16 @@ class SuiteInfo(SuiteInfoBase): return self._function_info[name] -class FunctionInfo(SuiteInfo): - def __init__(self, tree): - DefnInfo.__init__(self, tree) - suite = tree[-1] - if len(suite) >= 4: - found, vars = match(DOCSTRING_STMT_PATTERN, suite[3]) - if found: - self._docstring = eval(vars['docstring']) - SuiteInfoBase.__init__(self) - self._extract_info(suite) +class FunctionInfo(SuiteInfoBase, SuiteFuncInfo): + def __init__(self, tree = None): + self._name = tree[2][1] + SuiteInfoBase.__init__(self, tree and tree[-1] or None) class ClassInfo(SuiteInfoBase): - def __init__(self, tree): - SuiteInfoBase.__init__(self) - DefnInfo.__init__(self, tree) - self._extract_info(tree[-1]) + def __init__(self, tree = None): + self._name = tree[2][1] + SuiteInfoBase.__init__(self, tree and tree[-1] or None) def get_method_names(self): return self._function_info.keys() @@ -101,19 +102,40 @@ class ClassInfo(SuiteInfoBase): return self._function_info[name] -class ModuleInfo(SuiteInfo): - def __init__(self, tree, name=""): +class ModuleInfo(SuiteInfoBase, SuiteFuncInfo): + def __init__(self, tree = None, name = ""): self._name = name - SuiteInfo.__init__(self, tree) - found, vars = match(DOCSTRING_STMT_PATTERN, tree[1]) - if found: - self._docstring = vars["docstring"] + SuiteInfoBase.__init__(self, tree) + if tree: + found, vars = match(DOCSTRING_STMT_PATTERN, tree[1]) + if found: + self._docstring = vars["docstring"] from types import ListType, TupleType def match(pattern, data, vars=None): - """ + """Match `data' to `pattern', with variable extraction. + + pattern + Pattern to match against, possibly containing variables. + + data + Data to be checked and against which variables are extracted. + + vars + Dictionary of variables which have already been found. If not + provided, an empty dictionary is created. + + The `pattern' value may contain variables of the form ['varname'] which + are allowed to match anything. The value that is matched is returned as + part of a dictionary which maps 'varname' to the matched value. 'varname' + is not required to be a string object, but using strings makes patterns + and the code which uses them more readable. + + This function returns two values: a boolean indicating whether a match + was found and a dictionary mapping variable names to their associated + values. """ if vars is None: vars = {} @@ -131,6 +153,15 @@ def match(pattern, data, vars=None): return same, vars +# This pattern identifies compound statements, allowing them to be readily +# differentiated from simple statements. +# +COMPOUND_STMT_PATTERN = ( + symbol.stmt, + (symbol.compound_stmt, ['compound']) + ) + + # This pattern will match a 'stmt' node which *might* represent a docstring; # docstrings require that the statement which provides the docstring be the # first statement in the class or function, which this pattern does not check. diff --git a/Demo/parser/pprint.py b/Demo/parser/pprint.py index c4b815800c1..36d188805bc 100644 --- a/Demo/parser/pprint.py +++ b/Demo/parser/pprint.py @@ -1,7 +1,7 @@ # pprint.py # # Author: Fred L. Drake, Jr. -# fdrake@vt.edu +# fdrake@cnri.reston.va.us, fdrake@intr.net # # This is a simple little module I wrote to make life easier. I didn't # see anything quite like it in the library, though I may have overlooked @@ -9,35 +9,29 @@ # tuples with fairly non-descriptive content. This is modelled very much # after Lisp/Scheme - style pretty-printing of lists. If you find it # useful, thank small children who sleep at night. -# """Support to pretty-print lists, tuples, & dictionaries recursively. -Very simple, but at least somewhat useful, especially in debugging -data structures. +Very simple, but useful, especially in debugging data structures. -INDENT_PER_LEVEL -- Amount of indentation to use for each new - recursive level. The default is 1. This - must be a non-negative integer, and may be - set by the caller before calling pprint(). +Constants +--------- -MAX_WIDTH -- Maximum width of the display. This is only - used if the representation *can* be kept - less than MAX_WIDTH characters wide. May - be set by the user before calling pprint(). +INDENT_PER_LEVEL + Amount of indentation to use for each new recursive level. The + default is 1. This must be a non-negative integer, and may be set + by the caller before calling pprint(). -TAB_WIDTH -- The width represented by a single tab. This - value is typically 8, but 4 is the default - under MacOS. Can be changed by the user if - desired, but is probably not a good idea. +MAX_WIDTH + Maximum width of the display. This is only used if the + representation *can* be kept less than MAX_WIDTH characters wide. + May be set by the user before calling pprint(). -pprint(seq [, stream]) -- The pretty-printer. This takes a Python - object (presumably a sequence, but that - doesn't matter) and an optional output - stream. See the function documentation - for details. +TAB_WIDTH + The width represented by a single tab. This value is typically 8, + but 4 is the default under MacOS. Can be changed by the user if + desired, but is probably not a good idea. """ - INDENT_PER_LEVEL = 1 MAX_WIDTH = 80 @@ -46,46 +40,45 @@ import os TAB_WIDTH = (os.name == 'mac' and 4) or 8 del os +from types import DictType, ListType, TupleType def _indentation(cols): - "Create tabbed indentation string COLS columns wide." - - # This is used to reduce the byte-count for the output, allowing - # files created using this module to use as little external storage - # as possible. This is primarily intended to minimize impact on - # a user's quota when storing resource files, or for creating output - # intended for transmission. + """Create tabbed indentation string. + cols + Width of the indentation, in columns. + """ return ((cols / TAB_WIDTH) * '\t') + ((cols % TAB_WIDTH) * ' ') - def pprint(seq, stream = None, indent = 0, allowance = 0): """Pretty-print a list, tuple, or dictionary. - pprint(seq [, stream]) ==> None + seq + List, tuple, or dictionary object to be pretty-printed. Other + object types are permitted by are not specially interpreted. - If STREAM is provided, output is written to that stream, otherwise - sys.stdout is used. Indentation is done according to - INDENT_PER_LEVEL, which may be set to any non-negative integer - before calling this function. The output written on the stream is - a perfectly valid representation of the Python object passed in, - with indentation to suite human-readable interpretation. The - output can be used as input without error, given readable - representations of all sequence elements are available via repr(). - Output is restricted to MAX_WIDTH columns where possible. The - STREAM parameter must support the write() method with a single - parameter, which will always be a string. The output stream may be - a StringIO.StringIO object if the result is needed as a string. + stream + Output stream. If not provided, `sys.stdout' is used. This + parameter must support the `write()' method with a single + parameter, which will always be a string. It may be a + `StringIO.StringIO' object if the result is needed as a + string. + + Indentation is done according to `INDENT_PER_LEVEL', which may be + set to any non-negative integer before calling this function. The + output written on the stream is a perfectly valid representation + of the Python object passed in, with indentation to assist + human-readable interpretation. The output can be used as input + without error, given readable representations of all elements are + available via `repr()'. Output is restricted to `MAX_WIDTH' + columns where possible. """ - if stream is None: import sys stream = sys.stdout - from types import DictType, ListType, TupleType - rep = `seq` typ = type(seq) sepLines = len(rep) > (MAX_WIDTH - 1 - indent - allowance) @@ -140,4 +133,4 @@ def pprint(seq, stream = None, indent = 0, allowance = 0): # -# end of pprint.py +# end of file diff --git a/Demo/parser/simple.py b/Demo/parser/simple.py new file mode 100644 index 00000000000..184e2fe5d0a --- /dev/null +++ b/Demo/parser/simple.py @@ -0,0 +1 @@ +def f(): "maybe a docstring" diff --git a/Doc/lib/libparser.tex b/Doc/lib/libparser.tex index 4398177759a..2264c895375 100644 --- a/Doc/lib/libparser.tex +++ b/Doc/lib/libparser.tex @@ -236,19 +236,25 @@ to the descriptions of each function for detailed information. \subsection{AST Objects} AST objects (returned by \code{expr()}, \code{suite()}, and -\code{tuple2ast()}, described above) have no methods of their own. +\code{sequence2ast()}, described above) have no methods of their own. Some of the functions defined which accept an AST object as their first argument may change to object methods in the future. Ordered and equality comparisons are supported between AST objects. -\subsection{Example} +\subsection{Examples} The parser modules allows operations to be performed on the parse tree of Python source code before the bytecode is generated, and provides for inspection of the parse tree for information gathering purposes as -well. While many useful operations may take place between parsing and +well. Two examples are presented. The simple example demonstrates +emulation of the \code{compile()} built-in function and the complex +example shows the use of a parse tree for information discovery. + +\subsubsection{Emulation of {\tt compile()}} + +While many useful operations may take place between parsing and bytecode generation, the simplest operation is to do nothing. For this purpose, using the \code{parser} module to produce an intermediate data structure is equivelent to the code @@ -273,6 +279,25 @@ as an AST object: 10 \end{verbatim} +An application which needs both AST and code objects can package this +code into readily available functions: + +\begin{verbatim} +import parser + +def load_suite(source_string): + ast = parser.suite(source_string) + code = parser.compileast(ast) + return ast, code + +def load_expression(source_string): + ast = parser.expr(source_string) + code = parser.compileast(ast) + return ast, code +\end{verbatim} + +\subsubsection{Information Discovery} + Some applications can benfit from access to the parse tree itself, and can take advantage of the intermediate data structure provided by the \code{parser} module. The remainder of this section of examples will @@ -293,6 +318,16 @@ operations on behalf of the caller. All source files mentioned here which are not part of the Python installation are located in the \file{Demo/parser} directory of the distribution. +The dynamic nature of Python allows the programmer a great deal of +flexibility, but most modules need only a limited measure of this when +defining classes, functions, and methods. In this example, the only +definitions that will be considered are those which are defined in the +top level of their context, e.g., a function defined by a \code{def} +statement at column zero of a module, but not a function defined +within a branch of an \code{if} ... \code{else} construct, thought +there are some good reasons for doing so in some situations. Nesting +of definitions will be handled by the code developed in the example. + To construct the upper-level extraction methods, we need to know what the parse tree structure looks like and how much of it we actually need to be concerned about. Python uses a moderately deep parse tree, @@ -300,7 +335,8 @@ so there are a large number of intermediate nodes. It is important to read and understand the formal grammar used by Python. This is specified in the file \file{Grammar/Grammar} in the distribution. Consider the simplest case of interest when searching for docstrings: -a module consisting of a docstring and nothing else: +a module consisting of a docstring and nothing else. (See file +\file{docstring.py}.) \begin{verbatim} """Some documentation. @@ -376,7 +412,7 @@ extraction, we can safely require that the tree be in tuple form rather than list form, allowing a simple variable representation to be \code{['variable\_name']}. A simple recursive function can implement the pattern matching, returning a boolean and a dictionary of variable -name to value mappings. +name to value mappings. (See file \file{example.py}.) \begin{verbatim} from types import ListType, TupleType @@ -399,32 +435,36 @@ def match(pattern, data, vars=None): \end{verbatim} Using this simple recursive pattern matching function and the symbolic -node types, the pattern for the candidate docstring subtrees becomes: +node types, the pattern for the candidate docstring subtrees becomes +fairly readable. (See file \file{example.py}.) \begin{verbatim} ->>> DOCSTRING_STMT_PATTERN = ( -... symbol.stmt, -... (symbol.simple_stmt, -... (symbol.small_stmt, -... (symbol.expr_stmt, -... (symbol.testlist, -... (symbol.test, -... (symbol.and_test, -... (symbol.not_test, -... (symbol.comparison, -... (symbol.expr, -... (symbol.xor_expr, -... (symbol.and_expr, -... (symbol.shift_expr, -... (symbol.arith_expr, -... (symbol.term, -... (symbol.factor, -... (symbol.power, -... (symbol.atom, -... (token.STRING, ['docstring']) -... )))))))))))))))), -... (token.NEWLINE, '') -... )) +import symbol +import token + +DOCSTRING_STMT_PATTERN = ( + symbol.stmt, + (symbol.simple_stmt, + (symbol.small_stmt, + (symbol.expr_stmt, + (symbol.testlist, + (symbol.test, + (symbol.and_test, + (symbol.not_test, + (symbol.comparison, + (symbol.expr, + (symbol.xor_expr, + (symbol.and_expr, + (symbol.shift_expr, + (symbol.arith_expr, + (symbol.term, + (symbol.factor, + (symbol.power, + (symbol.atom, + (token.STRING, ['docstring']) + )))))))))))))))), + (token.NEWLINE, '') + )) \end{verbatim} Using the \code{match()} function with this pattern, extracting the @@ -453,6 +493,160 @@ sibling nodes to match without regard to number. A more elaborate matching function could be used to overcome this limitation, but this is sufficient for the example. +Given the ability to determine whether a statement might be a +docstring and extract the actual string from the statement, some work +needs to be performed to walk the parse tree for an entire module and +extract information about the names defined in each context of the +module and associate any docstrings with the names. The code to +perform this work is not complicated, but bears some explanation. + +The public interface to the classes is straightforward and should +probably be somewhat more flexible. Each ``major'' block of the +module is described by an object providing several methods for inquiry +and a constructor which accepts at least the subtree of the complete +parse tree which it represents. The \code{ModuleInfo} constructor +accepts an optional \code{\var{name}} parameter since it cannot +otherwise determine the name of the module. + +The public classes include \code{ClassInfo}, \code{FunctionInfo}, +and \code{ModuleInfo}. All objects provide the +methods \code{get_name()}, \code{get_docstring()}, +\code{get_class_names()}, and \code{get_class_info()}. The +\code{ClassInfo} objects support \code{get_method_names()} and +\code{get_method_info()} while the other classes provide +\code{get_function_names()} and \code{get_function_info()}. + +Within each of the forms of code block that the public classes +represent, most of the required information is in the same form and is +access in the same way, with classes having the distinction that +functions defined at the top level are referred to as ``methods.'' +Since the difference in nomenclature reflects a real semantic +distinction from functions defined outside of a class, our +implementation needs to maintain the same measure of distinction. +Hence, most of the functionality of the public classes can be +implemented in a common base class, \code{SuiteInfoBase}, with the +accessors for function and method information provided elsewhere. +Note that there is only one class which represents function and method +information; this mirrors the use of the \code{def} statement to +define both types of functions. + +Most of the accessor functions are declared in \code{SuiteInfoBase} +and do not need to be overriden by subclasses. More importantly, the +extraction of most information from a parse tree is handled through a +method called by the \code{SuiteInfoBase} constructor. The example +code for most of the classes is clear when read alongside the formal +grammar, but the method which recursively creates new information +objects requires further examination. Here is the relevant part of +the \code{SuiteInfoBase} definition from \file{example.py}: + +\begin{verbatim} +class SuiteInfoBase: + _docstring = '' + _name = '' + + def __init__(self, tree = None): + self._class_info = {} + self._function_info = {} + if tree: + self._extract_info(tree) + + def _extract_info(self, tree): + # extract docstring + if len(tree) == 2: + found, vars = match(DOCSTRING_STMT_PATTERN[1], tree[1]) + else: + found, vars = match(DOCSTRING_STMT_PATTERN, tree[3]) + if found: + self._docstring = eval(vars['docstring']) + # discover inner definitions + for node in tree[1:]: + found, vars = match(COMPOUND_STMT_PATTERN, node) + if found: + cstmt = vars['compound'] + if cstmt[0] == symbol.funcdef: + name = cstmt[2][1] + self._function_info[name] = FunctionInfo(cstmt) + elif cstmt[0] == symbol.classdef: + name = cstmt[2][1] + self._class_info[name] = ClassInfo(cstmt) +\end{verbatim} + +After initializing some internal state, the constructor calls the +\code{_extract_info()} method. This method performs the bulk of the +information extraction which takes place in the entire example. The +extraction has two distinct phases: the location of the docstring for +the parse tree passed in, and the discovery of additional definitions +within the code block represented by the parse tree. + +The initial \code{if} test determines whether the nested suite is of +the ``short form'' or the ``long form.'' The short form is used when +the code block is on the same line as the definition of the code +block, as in + +\begin{verbatim} +def square(x): "Square an argument."; return x ** 2 +\end{verbatim} + +while the long form uses an indented block and allows nested +definitions: + +\begin{verbatim} +def make_power(exp): + "Make a function that raises an argument to the exponent `exp'." + def raiser(x, y=exp): + return x ** y + return raiser +\end{verbatim} + +When the short form is used, the code block may contain a docstring as +the first, and possibly only, \code{small_stmt} element. The +extraction of such a docstring is slightly different and requires only +a portion of the complete pattern used in the more common case. As +given in the code, the docstring will only be found if there is only +one \code{small_stmt} node in the \code{simple_stmt} node. Since most +functions and methods which use the short form do not provide +docstring, this may be considered sufficient. The extraction of the +docstring proceeds using the \code{match()} function as described +above, and the value of the docstring is stored as an attribute of the +\code{SuiteInfoBase} object. + +After docstring extraction, the operates a simple definition discovery +algorithm on the \code{stmt} nodes of the \code{suite} node. The +special case of the short form is not tested; since there are no +\code{stmt} nodes in the short form, the algorithm will silently skip +the single \code{simple_stmt} node and correctly not discover any +nested definitions. + +Each statement in the code block bing examined is categorized as being +a class definition, function definition (including methods), or +something else. For the definition statements, the name of the +element being defined is extracted and representation object +appropriate to the definition is created with the defining subtree +passed as an argument to the constructor. The repesentation objects +are stored in instance variables and may be retrieved by name using +the appropriate accessor methods. + +The public classes provide any accessors required which are more +specific than those provided by the \code{SuiteInfoBase} class, but +the real extraction algorithm remains common to all forms of code +blocks. A high-level function can be used to extract the complete set +of information from a source file: + +\begin{verbatim} +def get_docs(fileName): + source = open(fileName).read() + import os + basename = os.path.basename(os.path.splitext(fileName)[0]) + import parser + ast = parser.suite(source) + tup = parser.ast2tuple(ast) + return ModuleInfo(tup, basename) +\end{verbatim} + +This provides an easy-to-use interface to the documentation of a +module. If information is required which is not extracted by the code +of this example, the code may be extended at clearly defined points to +provide additional capabilities. %% diff --git a/Doc/libparser.tex b/Doc/libparser.tex index 4398177759a..2264c895375 100644 --- a/Doc/libparser.tex +++ b/Doc/libparser.tex @@ -236,19 +236,25 @@ to the descriptions of each function for detailed information. \subsection{AST Objects} AST objects (returned by \code{expr()}, \code{suite()}, and -\code{tuple2ast()}, described above) have no methods of their own. +\code{sequence2ast()}, described above) have no methods of their own. Some of the functions defined which accept an AST object as their first argument may change to object methods in the future. Ordered and equality comparisons are supported between AST objects. -\subsection{Example} +\subsection{Examples} The parser modules allows operations to be performed on the parse tree of Python source code before the bytecode is generated, and provides for inspection of the parse tree for information gathering purposes as -well. While many useful operations may take place between parsing and +well. Two examples are presented. The simple example demonstrates +emulation of the \code{compile()} built-in function and the complex +example shows the use of a parse tree for information discovery. + +\subsubsection{Emulation of {\tt compile()}} + +While many useful operations may take place between parsing and bytecode generation, the simplest operation is to do nothing. For this purpose, using the \code{parser} module to produce an intermediate data structure is equivelent to the code @@ -273,6 +279,25 @@ as an AST object: 10 \end{verbatim} +An application which needs both AST and code objects can package this +code into readily available functions: + +\begin{verbatim} +import parser + +def load_suite(source_string): + ast = parser.suite(source_string) + code = parser.compileast(ast) + return ast, code + +def load_expression(source_string): + ast = parser.expr(source_string) + code = parser.compileast(ast) + return ast, code +\end{verbatim} + +\subsubsection{Information Discovery} + Some applications can benfit from access to the parse tree itself, and can take advantage of the intermediate data structure provided by the \code{parser} module. The remainder of this section of examples will @@ -293,6 +318,16 @@ operations on behalf of the caller. All source files mentioned here which are not part of the Python installation are located in the \file{Demo/parser} directory of the distribution. +The dynamic nature of Python allows the programmer a great deal of +flexibility, but most modules need only a limited measure of this when +defining classes, functions, and methods. In this example, the only +definitions that will be considered are those which are defined in the +top level of their context, e.g., a function defined by a \code{def} +statement at column zero of a module, but not a function defined +within a branch of an \code{if} ... \code{else} construct, thought +there are some good reasons for doing so in some situations. Nesting +of definitions will be handled by the code developed in the example. + To construct the upper-level extraction methods, we need to know what the parse tree structure looks like and how much of it we actually need to be concerned about. Python uses a moderately deep parse tree, @@ -300,7 +335,8 @@ so there are a large number of intermediate nodes. It is important to read and understand the formal grammar used by Python. This is specified in the file \file{Grammar/Grammar} in the distribution. Consider the simplest case of interest when searching for docstrings: -a module consisting of a docstring and nothing else: +a module consisting of a docstring and nothing else. (See file +\file{docstring.py}.) \begin{verbatim} """Some documentation. @@ -376,7 +412,7 @@ extraction, we can safely require that the tree be in tuple form rather than list form, allowing a simple variable representation to be \code{['variable\_name']}. A simple recursive function can implement the pattern matching, returning a boolean and a dictionary of variable -name to value mappings. +name to value mappings. (See file \file{example.py}.) \begin{verbatim} from types import ListType, TupleType @@ -399,32 +435,36 @@ def match(pattern, data, vars=None): \end{verbatim} Using this simple recursive pattern matching function and the symbolic -node types, the pattern for the candidate docstring subtrees becomes: +node types, the pattern for the candidate docstring subtrees becomes +fairly readable. (See file \file{example.py}.) \begin{verbatim} ->>> DOCSTRING_STMT_PATTERN = ( -... symbol.stmt, -... (symbol.simple_stmt, -... (symbol.small_stmt, -... (symbol.expr_stmt, -... (symbol.testlist, -... (symbol.test, -... (symbol.and_test, -... (symbol.not_test, -... (symbol.comparison, -... (symbol.expr, -... (symbol.xor_expr, -... (symbol.and_expr, -... (symbol.shift_expr, -... (symbol.arith_expr, -... (symbol.term, -... (symbol.factor, -... (symbol.power, -... (symbol.atom, -... (token.STRING, ['docstring']) -... )))))))))))))))), -... (token.NEWLINE, '') -... )) +import symbol +import token + +DOCSTRING_STMT_PATTERN = ( + symbol.stmt, + (symbol.simple_stmt, + (symbol.small_stmt, + (symbol.expr_stmt, + (symbol.testlist, + (symbol.test, + (symbol.and_test, + (symbol.not_test, + (symbol.comparison, + (symbol.expr, + (symbol.xor_expr, + (symbol.and_expr, + (symbol.shift_expr, + (symbol.arith_expr, + (symbol.term, + (symbol.factor, + (symbol.power, + (symbol.atom, + (token.STRING, ['docstring']) + )))))))))))))))), + (token.NEWLINE, '') + )) \end{verbatim} Using the \code{match()} function with this pattern, extracting the @@ -453,6 +493,160 @@ sibling nodes to match without regard to number. A more elaborate matching function could be used to overcome this limitation, but this is sufficient for the example. +Given the ability to determine whether a statement might be a +docstring and extract the actual string from the statement, some work +needs to be performed to walk the parse tree for an entire module and +extract information about the names defined in each context of the +module and associate any docstrings with the names. The code to +perform this work is not complicated, but bears some explanation. + +The public interface to the classes is straightforward and should +probably be somewhat more flexible. Each ``major'' block of the +module is described by an object providing several methods for inquiry +and a constructor which accepts at least the subtree of the complete +parse tree which it represents. The \code{ModuleInfo} constructor +accepts an optional \code{\var{name}} parameter since it cannot +otherwise determine the name of the module. + +The public classes include \code{ClassInfo}, \code{FunctionInfo}, +and \code{ModuleInfo}. All objects provide the +methods \code{get_name()}, \code{get_docstring()}, +\code{get_class_names()}, and \code{get_class_info()}. The +\code{ClassInfo} objects support \code{get_method_names()} and +\code{get_method_info()} while the other classes provide +\code{get_function_names()} and \code{get_function_info()}. + +Within each of the forms of code block that the public classes +represent, most of the required information is in the same form and is +access in the same way, with classes having the distinction that +functions defined at the top level are referred to as ``methods.'' +Since the difference in nomenclature reflects a real semantic +distinction from functions defined outside of a class, our +implementation needs to maintain the same measure of distinction. +Hence, most of the functionality of the public classes can be +implemented in a common base class, \code{SuiteInfoBase}, with the +accessors for function and method information provided elsewhere. +Note that there is only one class which represents function and method +information; this mirrors the use of the \code{def} statement to +define both types of functions. + +Most of the accessor functions are declared in \code{SuiteInfoBase} +and do not need to be overriden by subclasses. More importantly, the +extraction of most information from a parse tree is handled through a +method called by the \code{SuiteInfoBase} constructor. The example +code for most of the classes is clear when read alongside the formal +grammar, but the method which recursively creates new information +objects requires further examination. Here is the relevant part of +the \code{SuiteInfoBase} definition from \file{example.py}: + +\begin{verbatim} +class SuiteInfoBase: + _docstring = '' + _name = '' + + def __init__(self, tree = None): + self._class_info = {} + self._function_info = {} + if tree: + self._extract_info(tree) + + def _extract_info(self, tree): + # extract docstring + if len(tree) == 2: + found, vars = match(DOCSTRING_STMT_PATTERN[1], tree[1]) + else: + found, vars = match(DOCSTRING_STMT_PATTERN, tree[3]) + if found: + self._docstring = eval(vars['docstring']) + # discover inner definitions + for node in tree[1:]: + found, vars = match(COMPOUND_STMT_PATTERN, node) + if found: + cstmt = vars['compound'] + if cstmt[0] == symbol.funcdef: + name = cstmt[2][1] + self._function_info[name] = FunctionInfo(cstmt) + elif cstmt[0] == symbol.classdef: + name = cstmt[2][1] + self._class_info[name] = ClassInfo(cstmt) +\end{verbatim} + +After initializing some internal state, the constructor calls the +\code{_extract_info()} method. This method performs the bulk of the +information extraction which takes place in the entire example. The +extraction has two distinct phases: the location of the docstring for +the parse tree passed in, and the discovery of additional definitions +within the code block represented by the parse tree. + +The initial \code{if} test determines whether the nested suite is of +the ``short form'' or the ``long form.'' The short form is used when +the code block is on the same line as the definition of the code +block, as in + +\begin{verbatim} +def square(x): "Square an argument."; return x ** 2 +\end{verbatim} + +while the long form uses an indented block and allows nested +definitions: + +\begin{verbatim} +def make_power(exp): + "Make a function that raises an argument to the exponent `exp'." + def raiser(x, y=exp): + return x ** y + return raiser +\end{verbatim} + +When the short form is used, the code block may contain a docstring as +the first, and possibly only, \code{small_stmt} element. The +extraction of such a docstring is slightly different and requires only +a portion of the complete pattern used in the more common case. As +given in the code, the docstring will only be found if there is only +one \code{small_stmt} node in the \code{simple_stmt} node. Since most +functions and methods which use the short form do not provide +docstring, this may be considered sufficient. The extraction of the +docstring proceeds using the \code{match()} function as described +above, and the value of the docstring is stored as an attribute of the +\code{SuiteInfoBase} object. + +After docstring extraction, the operates a simple definition discovery +algorithm on the \code{stmt} nodes of the \code{suite} node. The +special case of the short form is not tested; since there are no +\code{stmt} nodes in the short form, the algorithm will silently skip +the single \code{simple_stmt} node and correctly not discover any +nested definitions. + +Each statement in the code block bing examined is categorized as being +a class definition, function definition (including methods), or +something else. For the definition statements, the name of the +element being defined is extracted and representation object +appropriate to the definition is created with the defining subtree +passed as an argument to the constructor. The repesentation objects +are stored in instance variables and may be retrieved by name using +the appropriate accessor methods. + +The public classes provide any accessors required which are more +specific than those provided by the \code{SuiteInfoBase} class, but +the real extraction algorithm remains common to all forms of code +blocks. A high-level function can be used to extract the complete set +of information from a source file: + +\begin{verbatim} +def get_docs(fileName): + source = open(fileName).read() + import os + basename = os.path.basename(os.path.splitext(fileName)[0]) + import parser + ast = parser.suite(source) + tup = parser.ast2tuple(ast) + return ModuleInfo(tup, basename) +\end{verbatim} + +This provides an easy-to-use interface to the documentation of a +module. If information is required which is not extracted by the code +of this example, the code may be extended at clearly defined points to +provide additional capabilities. %%