diff --git a/Doc/ref.tex b/Doc/ref.tex new file mode 100644 index 00000000000..6af7535cf18 --- /dev/null +++ b/Doc/ref.tex @@ -0,0 +1,1020 @@ +% Format this file with latex. + +\documentstyle[myformat]{report} + +\title{\bf + Python Reference Manual \\ + {\em Incomplete Draft} +} + +\author{ + Guido van Rossum \\ + Dept. CST, CWI, Kruislaan 413 \\ + 1098 SJ Amsterdam, The Netherlands \\ + E-mail: {\tt guido@cwi.nl} +} + +\begin{document} + +\pagenumbering{roman} + +\maketitle + +\begin{abstract} + +\noindent +Python is a simple, yet powerful programming language that bridges the +gap between C and shell programming, and is thus ideally suited for +``throw-away programming'' +and rapid prototyping. Its syntax is put +together from constructs borrowed from a variety of other languages; +most prominent are influences from ABC, C, Modula-3 and Icon. + +The Python interpreter is easily extended with new functions and data +types implemented in C. Python is also suitable as an extension +language for highly customizable C applications such as editors or +window managers. + +Python is available for various operating systems, amongst which +several flavors of {\UNIX}, Amoeba, the Apple Macintosh O.S., +and MS-DOS. + +This reference manual describes the syntax and ``core semantics'' of +the language. It is terse, but exact and complete. The semantics of +non-essential built-in object types and of the built-in functions and +modules are described in the {\em Library Reference} document. For an +informal introduction to the language, see the {\em Tutorial} +document. + +\end{abstract} + +\pagebreak + +\tableofcontents + +\pagebreak + +\pagenumbering{arabic} + +\chapter{Introduction} + +This reference manual describes the Python programming language. +It is not intended as a tutorial. + +\chapter{Lexical analysis} + +A Python program is read by a {\em parser}. +Input to the parser is a stream of {\em tokens}, generated +by the {\em lexical analyzer}. + +\section{Line structure} + +A Python program is divided in a number of logical lines. +Statements may not straddle logical line boundaries except where +explicitly allowed by the syntax. +To this purpose, the end of a logical line +is represented by the token NEWLINE. + +\subsection{Comments} + +A comment starts with a hash character (\verb/#/) and ends at the end +of the physical line. Comments are ignored by the syntax. +A hash character in a string literal does not start a comment. + +\subsection{Line joining} + +Physical lines may be joined into logical lines using backslash +characters (\verb/\/), as follows. +If a physical line ends in a backslash that is not part of a string +literal or comment, it is joined with +the following forming a single logical line, deleting the backslash +and the following end-of-line character. More than two physical +lines may be joined together in this way. + +\subsection{Blank lines} + +A physical line that is not the continuation of the previous line +and contains only spaces, tabs and possibly a comment, is ignored +(i.e., no NEWLINE token is generated), +except that during interactive input of statements, an empty +physical line terminates a multi-line statement. + +\subsection{Indentation} + +Spaces and tabs at the beginning of a line are used to compute +the indentation level of the line, which in turn is used to determine +the grouping of statements. + +First, each tab is replaced by one to eight spaces such that the column number +of the next character is a multiple of eight (counting from zero). +The column number of the first non-space character then defines the +line's indentation. +Indentation cannot be split over multiple physical lines using +backslashes. + +The indentation levels of consecutive lines are used to generate +INDENT and DEDENT tokens, using a stack, as follows. + +Before the first line of the file is read, a single zero is pushed on +the stack; this will never be popped off again. The numbers pushed +on the stack will always be strictly increasing from bottom to top. +At the beginning of each logical line, the line's indentation level +is compared to the top of the stack. +If it is equal, nothing happens. +If it larger, it is pushed on the stack, and one INDENT token is generated. +If it is smaller, it {\em must} be one of the numbers occurring on the +stack; all numbers on the stack that are larger are popped off, +and for each number popped off a DEDENT token is generated. +At the end of the file, a DEDENT token is generated for each number +remaining on the stack that is larger than zero. + +\section{Other tokens} + +Besides NEWLINE, INDENT and DEDENT, the following categories of tokens +exist: identifiers, keywords, literals, operators, and delimiters. +Spaces and tabs are not tokens, but serve to delimit tokens. +Where ambiguity exists, a token comprises the longest possible +string that forms a legal token, when reading from left to right. + +Tokens are described using an extended regular expression notation. +This is similar to the extended BNF notation used later, except that +the notation <...> is used to give an informal description of a character, +and that spaces and tabs are not to be ignored. + +\section{Identifiers} + +Identifiers are described by the following regular expressions: + +\begin{verbatim} +identifier: (letter|'_') (letter|digit|'_')* +letter: lowercase | uppercase +lowercase: 'a'|'b'|...|'z' +uppercase: 'A'|'B'|...|'Z' +digit: '0'|'1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9' +\end{verbatim} + +Identifiers are unlimited in length. +Upper and lower case letters are different. + +\section{Keywords} + +The following tokens are used as reserved words, +or keywords of the language, +and may not be used as ordinary identifiers. +They must be spelled exactly as written here: + +{\tt + and + break + class + continue + def + del + elif + else + except + finally + for + from + if + import + in + is + not + or + pass + print + raise + return + try + while +} + +\section{Literals} + +\subsection{String literals} + +String literals are described by the following regular expressions: + +\begin{verbatim} +stringliteral: '\'' stringitem* '\'' +stringitem: stringchar | escapeseq +stringchar: +escapeseq: '\\' +\end{verbatim} + +String literals cannot span physical line boundaries. +Escape sequences in strings are actually interpreted according to almost the +same rules as used by Standard C +(XXX which should be made explicit here), +except that \verb/\E/ is equivalent to \verb/\033/, +\verb/\"/ is not recognized, +newline characters cannot be escaped, and +{\em all unrecognized escape sequences are left in the string unchanged}. +(The latter rule is useful when debugging: if an escape sequence is +mistyped, the resulting output is more easily recognized as broken. +It also helps somewhat for string literals used as regular expressions +or otherwise passed to other modules that do their own escape handling.) + +\subsection{Numeric literals} + +There are three types of numeric literals: integers, long integers, +and floating point numbers. + +Integers and long integers are described by the following regular expressions: + +\begin{verbatim} +longinteger: integer ('l'|'L') +integer: decimalinteger | octinteger | hexinteger +decimalinteger: nonzerodigit digit* | '0' +octinteger: '0' octdigit+ +hexinteger: '0' ('x'|'X') hexdigit+ + +nonzerodigit: '1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9' +octdigit: '0'|'1'|'2'|'3'|'4'|'5'|'6'|'7' +hexdigit: digit|'a'|'b'|'c'|'d'|'e'|'f'|'A'|'B'|'C'|'D'|'E'|'F' +\end{verbatim} + +Floating point numbers are described by the following regular expressions: + +\begin{verbatim} +floatnumber: [intpart] fraction [exponent] | intpart ['.'] exponent +intpart: digit+ +fraction: '.' digit+ +exponent: ('e'|'E') ['+'|'-'] digit+ +\end{verbatim} + +\section{Operators} + +The following tokens are operators: + +\begin{verbatim} ++ - * / % +<< >> & | ^ ~ +< = == > <= <> != >= +\end{verbatim} + +\section{Delimiters} + +The following tokens are delimiters: + +\begin{verbatim} +( ) [ ] { } +; , : . ` +\end{verbatim} + +The following printing ASCII characters are currently not used; +their occurrence is an unconditional error: + +\begin{verbatim} +! @ $ " ? +\end{verbatim} + +\chapter{Execution model} + +(XXX This chapter should explain the general model +of the execution of Python code and +the evaluation of expressions. +It should introduce objects, values, code blocks, scopes, name spaces, +name binding, +types, sequences, numbers, mappings, +exceptions, and other technical terms needed to make the following +chapters concise and exact.) + +\chapter{Expressions and conditions} + +(From now on, extended BNF notation will be used to describe +syntax, not lexical analysis.) +(XXX Explain the notation.) + +This chapter explains the meaning of the elements of expressions and +conditions. Conditions are a superset of expressions, and a condition +may be used where an expression is required by enclosing it in +parentheses. The only place where an unparenthesized condition +is not allowed is on the right-hand side of the assignment operator, +because this operator is the same token (\verb/'='/) as used for +compasisons. + +The comma plays a somewhat special role in Python's syntax. +It is an operator with a lower precedence than all others, but +occasionally serves other purposes as well (e.g., it has special +semantics in print statements). When a comma is accepted by the +syntax, one of the syntactic categories \verb/expression_list/ +or \verb/condition_list/ is always used. + +When (one alternative of) a syntax rule has the form + +\begin{verbatim} +name: othername +\end{verbatim} + +and no semantics are given, the semantics of this form of \verb/name/ +are the same as for \verb/othername/. + +\section{Arithmetic conversions} + +When a description of an arithmetic operator below uses the phrase +``the numeric arguments are converted to a common type'', +this both means that if either argument is not a number, a +{\tt TypeError} exception is raised, and that otherwise +the following conversions are applied: + +\begin{itemize} +\item First, if either argument is a floating point number, + the other is converted to floating point; +\item else, if either argument is a long integer, + the other is converted to long integer; +\item otherwise, both must be short integers and no conversion + is necessary. +\end{itemize} + +(Note: ``short integers'' in Python are at least 32 bits in size; +``long integers'' are arbitrary precision integers.) + +\section{Atoms} + +Atoms are the most basic elements of expressions. +Forms enclosed in reverse quotes or various types of parentheses +or braces are also categorized syntactically as atoms. +Syntax rules for atoms: + +\begin{verbatim} +atom: identifier | literal | parenth_form | string_conversion +literal: stringliteral | integer | longinteger | floatnumber +parenth_form: enclosure | list_display | dict_display +enclosure: '(' [condition_list] ')' +list_display: '[' [condition_list] ']' +dict_display: '{' [key_datum (',' key_datum)* [','] '}' +key_datum: condition ':' condition +string_conversion:'`' condition_list '`' +\end{verbatim} + +\subsection{Identifiers (Names)} + +An identifier occurring as an atom is a reference to a local, global +or built-in name binding. If a name can be assigned to anywhere in a code +block, it refers to a local name throughout that code block. +Otherwise, it refers to a global name if one exists, else to a +built-in name. + +When the name is bound to an object, evaluation of the atom +yields that object. +When it is not bound, a {\tt NameError} exception +is raised, with the identifier as string parameter. + +\subsection{Literals} + +Evaluation of a literal yields an object of the given type +(string, integer, long integer, floating point number) +with the given value. +The value may be approximated in the case of floating point literals. + +All literals correspond to immutable data types, and hence the object's +identity is less important than its value. +Multiple evaluations of the same literal (either the same occurrence +in the program text or a different occurrence) may +obtain the same object or a different object with the same value. + +(In the original implementation, all literals in the same code block +with the same type and value yield the same object.) + +\subsection{Enclosures} + +An empty enclosure yields an empty tuple object. + +An enclosed condition list yields whatever that condition list yields. + +(Note that, except for empty tuples, tuples are not formed by +enclosure in parentheses, but rather by use of the comma operator.) + +\subsection{List displays} + +A list display yields a new list object. + +If it has no condition list, the list object has no items. +Otherwise, the elements of the condition list are evaluated +from left to right and inserted in the list object in that order. + +\subsection{Dictionary displays} + +A dictionary display yields a new dictionary object. + +The key/datum pairs are evaluated from left to right to +define the entries of the dictionary: +each key object is used as a key into the dictionary to store +the corresponding datum pair. + +Key objects must be strings, otherwise a {\tt TypeError} +exception is raised. +Clashes between keys are not detected; the last datum stored for a given +key value prevails. + +\subsection{String conversions} + +A string conversion evaluates the contained condition list and converts the +resulting object into a string according to rules specific to its type. + +If the object is a string, a number, \verb/None/, or a tuple, list or +dictionary containing only objects whose type is in this list, +the resulting +string is a valid Python expression which can be passed to the +built-in function \verb/eval()/ to yield an expression with the +same value (or an approximation, if floating point numbers are +involved). + +(In particular, converting a string adds quotes around it and converts +``funny'' characters to escape sequences that are safe to print.) + +It is illegal to attempt to convert recursive objects (e.g., +lists or dictionaries that -- directly or indirectly -- contain a reference +to themselves.) + +\section{Primaries} + +Primaries represent the most tightly bound operations of the language. +Their syntax is: + +\begin{verbatim} +primary: atom | attributeref | call | subscription | slicing +attributeref: primary '.' identifier +call: primary '(' [condition_list] ')' +subscription: primary '[' condition ']' +slicing: primary '[' [condition] ':' [condition] ']' +\end{verbatim} + +\subsection{Attribute references} + +\subsection{Calls} + +\subsection{Subscriptions} + +\subsection{Slicings} + +\section{Factors} + +Factors represent the unary numeric operators. +Their syntax is: + +\begin{verbatim} +factor: primary | '-' factor | '+' factor | '~' factor +\end{verbatim} + +The unary \verb/'-'/ operator yields the negative of its numeric argument. + +The unary \verb/'+'/ operator yields its numeric argument unchanged. + +The unary \verb/'~'/ operator yields the bit-wise negation of its +integral numerical argument. + +In all three cases, if the argument does not have the proper type, +a {\tt TypeError} exception is raised. + +\section{Terms} + +Terms represent the most tightly binding binary operators: + +\begin{verbatim} +term: factor | term '*' factor | term '/' factor | term '%' factor +\end{verbatim} + +The \verb/'*'/ operator yields the product of its arguments. +The arguments must either both be numbers, or one argument must be +a (short) integer and the other must be a string. +In the former case, the numbers are converted to a common type +and then multiplied together. +In the latter case, string repetition is performed; a negative +repetition factor yields the empty string. + +The \verb|'/'| operator yields the quotient of its arguments. +The numeric arguments are first converted to a common type. +(Short or long) integer division yields an integer of the same type, +truncating towards zero. +Division by zero raises a {\tt RuntimeError} exception. + +The \verb|'%'| operator yields the remainder from the division +of the first argument by the second. +The numeric arguments are first converted to a common type. +The outcome of $x % y$ is defined as $x - y*trunc(x/y)$. +A zero right argument raises a {\tt RuntimeError} exception. +The arguments may be floating point numbers, e.g., +$3.14 % 0.7$ equals $0.34$. + +\section{Arithmetic expressions} + +\begin{verbatim} +arith_expr: term | arith_expr '+' term | arith_expr '-' term +\end{verbatim} + +The \verb|'+'| operator yields the sum of its arguments. +The arguments must either both be numbers, or both strings. +In the former case, the numbers are converted to a common type +and then added together. +In the latter case, the strings are concatenated directly, +without inserting a space. + +The \verb|'-'| operator yields the difference of its arguments. +The numeric arguments are first converted to a common type. + +\section{Shift expressions} + +\begin{verbatim} +shift_expr: arith_expr | shift_expr '<<' arith_expr | shift_expr '>>' arith_expr +\end{verbatim} + +These operators accept short integers as arguments only. +They shift their left argument to the left or right by the number of bits +given by the right argument. Shifts are ``logical'', e.g., bits shifted +out on one end are lost, and bits shifted in are zero; +negative numbers are shifted as if they were unsigned in C. +Negative shift counts and shift counts greater than {\em or equal to} +the word size yield undefined results. + +\section{Bitwise AND expressions} + +\begin{verbatim} +and_expr: shift_expr | and_expr '&' shift_expr +\end{verbatim} + +This operator yields the bitwise AND of its arguments, +which must be short integers. + +\section{Bitwise XOR expressions} + +\begin{verbatim} +xor_expr: and_expr | xor_expr '^' and_expr +\end{verbatim} + +This operator yields the bitwise exclusive OR of its arguments, +which must be short integers. + +\section{Bitwise OR expressions} + +\begin{verbatim} +or_expr: xor_expr | or_expr '|' xor_expr +\end{verbatim} + +This operator yields the bitwise OR of its arguments, +which must be short integers. + +\section{Expressions and expression lists} + +\begin{verbatim} +expression: or_expression +expr_list: expression (',' expression)* [','] +\end{verbatim} + +An expression list containing at least one comma yields a new tuple. +The length of the tuple is the number of expressions in the list. +The expressions are evaluated from left to right. + +The trailing comma is required only to create a single tuple; +it is optional in all other cases (a single expression without +a trailing comma doesn't create a tuple, but rather yields the +value of that expression). + +To create an empty tuple, use an empty pair of parentheses: \verb/()/. + +\section{Comparisons} + +\begin{verbatim} +comparison: expression (comp_operator expression)* +comp_operator: '<'|'>'|'='|'=='|'>='|'<='|'<>'|'!='|['not'] 'in'|is' ['not'] +\end{verbatim} + +Comparisons yield integer value: 1 for true, 0 for false. + +Comparisons can be chained arbitrarily, +e.g., $x < y <= z$ is equivalent to +$x < y$ {\tt and} $y <= z$, except that $y$ is evaluated only once +(but in both cases $z$ is not evaluated at all when $x < y$ is +found to be false). + +Formally, $e_0 op_1 e_1 op_2 e_2 ...e_{n-1} op_n e_n$ is equivalent to +$e_0 op_1 e_1$ {\tt and} $e_1 op_2 e_2$ {\tt and} ... {\tt and} +$e_{n-1} op_n e_n$, except that each expression is evaluated at most once. + +Note that $e_0 op_1 e_1 op_2 e_2$ does not imply any kind of comparison +between $e_0$ and $e_2$, e.g., $x < y > z$ is perfectly legal. + +For the benefit of C programmers, +the comparison operators \verb/=/ and \verb/==/ are equivalent, +and so are \verb/<>/ and \verb/!=/. +Use of the C variants is discouraged. + +The operators {\tt '<', '>', '=', '>=', '<='}, and {\tt '<>'} compare +the values of two objects. The objects needn't have the same type. +If both are numbers, they are compared to a common type. +Otherwise, objects of different types {\em always} compare unequal, +and are ordered consistently but arbitrarily, except that +the value \verb\None\ compares smaller than the values of any other type. + +(This unusual +definition of comparison is done to simplify the definition of +operations like sorting and the \verb/in/ and \verb/not in/ operators.) + +Comparison of objects of the same type depends on the type: + +\begin{itemize} +\item Numbers are compared arithmetically. +\item Strings are compared lexicographically using the numeric + equivalents (the result of the built-in function ord()) + of their characters. +\item Tuples and lists are compared lexicographically + using comparison of corresponding items. +\item Dictionaries compare unequal unless they are the same object; + the choice whether one dictionary object is considered smaller + or larger than another one is made arbitrarily but + consistently within one execution of a program. +\item The latter rule is also used for most other built-in types. +\end{itemize} + +The operators \verb\in\ and \verb\not in\ test for sequence membership: +if $y$ is a sequence, $x {\tt in} y$ is true if and only if there exists +an index $i$ such that $x = y_i$. +$x {\tt not in} y$ yields the inverse truth value. +The exception {\tt TypeError} is raised when $y$ is not a sequence, +or when $y$ is a string and $x$ is not a string of length one. + +The operators \verb\is\ and \verb\is not\ compare object identity: +$x {\tt is} y$ is true if and only if $x$ and $y$ are the same object. +$x {\tt is not} y$ yields the inverse truth value. + +\section{Boolean operators} + +\begin{verbatim} +condition: or_test +or_test: and_test | or_test 'or' and_test +and_test: not_test | and_test 'and' not_test +not_test: comparison | 'not' not_test +\end{verbatim} + +In the context of Boolean operators, and also when conditions are +used by control flow statements, the following values are interpreted +as false: None, numeric zero of all types, empty sequences (strings, +tuples and lists), and empty mappings (dictionaries). +All other values are interpreted as true. + +The operator \verb\not\ yields 1 if its argument is false, 0 otherwise. + +The condition $x {\tt and} y$ first evaluates $x$; if $x$ is false, +$x$ is returned; otherwise, $y$ is evaluated and returned. + +The condition $x {\tt or} y$ first evaluates $x$; if $x$ is true, +$x$ is returned; otherwise, $y$ is evaluated and returned. + +(Note that \verb\and\ and \verb\or\ do not restrict the value and type +they return to 0 and 1, but rather return the last evaluated argument. +This is sometimes useful, e.g., if $s$ is a string, which should be +replaced by a default value if it is empty, $s {\tt or} 'foo'$ +returns the desired value. Because \verb\not\ has to invent a value +anyway, it does not bother to return a value of the same type as its +argument, so \verb\not 'foo'\ yields $0$, not $''$.) + +\chapter{Simple statements} + +Simple statements are comprised within a single logical line. +Several simple statements may occor on a single line separated +by semicolons. The syntax for simple statements is: + +\begin{verbatim} +stmt_list: simple_stmt (';' simple_stmt)* [';'] +simple_stmt: expression_stmt + | assignment + | pass_stmt + | del_stmt + | print_stmt + | return_stmt + | raise_stmt + | break_stmt + | continue_stmt + | import_stmt +\end{verbatim} + +\section{Expression statements} + +\begin{verbatim} +expression_stmt: expression_list +\end{verbatim} + +An expression statement evaluates the expression list (which may +be a single expression). +If the value is not \verb\None\, it is converted to a string +using the rules for string conversions, and the resulting string +is written to standard output on a line by itself. + +(The exception for \verb\None\ is made so that procedure calls, +which are syntactically equivalent to expressions, +do not cause any output.) + +\section{Assignments} + +\begin{verbatim} +assignment: target_list ('=' target_list)* '=' expression_list +target_list: target (',' target)* [','] +target: identifier | '(' target_list ')' | '[' target_list ']' + | attributeref | subscription | slicing +\end{verbatim} + +(See the section on primaries for the definition of the last +three symbols.) + +An assignment evaluates the expression list (remember that this can +be a single expression or a comma-separated list, +the latter yielding a tuple) +and assigns the single resulting object to each of the target lists, +from left to right. + +Assignment is defined recursively depending on the type of the +target. Where assignment is to part of a mutable object +(through an attribute reference, subscription or slicing), +the mutable object must ultimately perform the +assignment and decide about its validity, raising an exception +if the assignment is unacceptable. The rules observed by +various types and the exceptions raised are given with the +definition of the object types (some of which are defined +in the library reference). + +Assignment of an object to a target list is recursively +defined as follows. + +\begin{itemize} +\item +If the target list contains no commas (except in nested constructs): +the object is assigned to the single target contained in the list. + +\item +If the target list contains commas (that are not in nested constructs): +the object must be a tuple with as many items +as the list contains targets, and the items are assigned, from left +to right, to the corresponding targets. + +\end{itemize} + +Assignment of an object to a (non-list) +target is recursively defined as follows. + +\begin{itemize} + +\item +If the target is an identifier (name): +the object is bound to that name +in the current local scope. Any previous binding of the same name +is undone. + +\item +If the target is a target list enclosed in parentheses: +the object is assigned to that target list. + +\item +If the target is a target list enclosed in square brackets: +the object must be a list with as many items +as the target list contains targets, +and the list's items are assigned, from left to right, +to the corresponding targets. + +\item +If the target is an attribute reference: +The primary expression in the reference is evaluated. +It should yield an object with assignable attributes; +if this is not the case, a {\tt TypeError} exception is raised. +That object is then asked to assign the assigned object +to the given attribute; if it cannot perform the assignment, +it raises an exception. + +\item +If the target is a subscription: +The primary expression in the reference is evaluated. +It should yield either a mutable sequence object or a mapping +(dictionary) object. +Next, the subscript expression is evaluated. + +If the primary is a sequence object, the subscript must yield a +nonnegative integer smaller than the sequence's length, +and the sequence is asked to assign the assigned object +to its item with that index. + +If the primary is a mapping object, the subscript must have a +type compatible with the mapping's key type, +and the mapping is then asked to to create a key/datum pair +which maps the subscript to the assigned object. + +Various exceptions can be raised. + +\item +If the target is a slicing: +The primary expression in the reference is evaluated. +It should yield a mutable sequence object (currently only lists). +The assigned object should be a sequence object of the same type. +Next, the lower and upper bound expressions are evaluated, +insofar they are present; defaults are zero and the sequence's length. +The bounds should evaluate to (small) integers. +If either bound is negative, the sequence's length is added to it (once). +The resulting bounds are clipped to lie between zero +and the sequence's length, inclusive. +(XXX Shouldn't this description be with expressions?) +Finally, the sequence object is asked to replace the items +indicated by the slice with the items of the assigned sequence. +This may change the sequence's length, if it allows it. + +\end{itemize} + +(In the original implementation, the syntax for targets is taken +to be the same as for expressions, and invalid syntax is rejected +during the code generation phase, causing less detailed error +messages.) + +\section{The {\tt pass} statement} + +\begin{verbatim} +pass_stmt: 'pass' +\end{verbatim} + +{\tt pass} is a null operation -- when it is executed, +nothing happens. + +\section{The {\tt del} statement} + +\begin{verbatim} +del_stmt: 'del' target_list +\end{verbatim} + +Deletion is recursively defined similar to assignment. + +(XXX Rather that spelling it out in full details, +here are some hints.) + +Deletion of a target list recursively deletes each target, +from left to right. + +Deletion of a name removes the binding of that name (which must exist) +from the local scope. + +Deletion of attribute references, subscriptions and slicings +is passed to the primary object involved; deletion of a slicing +is in general equivalent to assignment of an empty slice of the +right type (but even this is determined by the sliced object). + +\section{The {\tt print} statement} + +\begin{verbatim} +print_stmt: 'print' [ condition (',' condition)* [','] ] +\end{verbatim} + +{\tt print} evaluates each condition in turn and writes the resulting +object to standard output (see below). +If an object is not a string, it is first converted to +a string using the rules for string conversions. +The (resulting or original) string is then written. +A space is written before each object is (converted and) written, +unless the output system believes it is positioned at the beginning +of a line. This is the case: (1) when no characters have been written +to standard output; or (2) when the last character written to +standard output is \verb/'\n'/; +or (3) when the last I/O operation +on standard output was not a \verb\print\ statement. + +Finally, +a \verb/'\n'/ character is written at the end, +unless the \verb\print\ statement ends with a comma. +This is the only action if the statement contains just the keyword +\verb\print\. + +Standard output is defined as the file object named \verb\stdout\ +in the built-in module \verb\sys\. If no such object exists, +or if it is not a writable file, a {\tt RuntimeError} exception is raised. +(The original implementation attempts to write to the system's original +standard output instead, but this is not safe, and should be fixed.) + +\section{The {\tt return} statement} + +\begin{verbatim} +return_stmt: 'return' [condition_list] +\end{verbatim} + +\verb\return\ may only occur syntactically nested in a function +definition, not within a nested class definition. + +If a condition list is present, it is evaluated, else \verb\None\ +is substituted. + +\verb\return\ leaves the current function call with the condition +list (or \verb\None\) as return value. + +When \verb\return\ passes control out of a \verb\try\ statement +with a \verb\finally\ clause, that finally clause is executed +before really leaving the function. +(XXX This should be made more exact, a la Modula-3.) + +\section{The {\tt raise} statement} + +\begin{verbatim} +raise_stmt: 'raise' condition [',' condition] +\end{verbatim} + +\verb\raise\ evaluates its first condition, which must yield +a string object. If there is a second condition, this is evaluated, +else \verb\None\ is substituted. + +It then raises the exception identified by the first object, +with the second one (or \verb\None\) as its parameter. + +\section{The {\tt break} statement} + +\begin{verbatim} +break_stmt: 'break' +\end{verbatim} + +\verb\break\ may only occur syntactically nested in a \verb\for\ +or \verb\while\ loop, not nested in a function or class definition. + +It terminates the neares enclosing loop, skipping the optional +\verb\else\ clause if the loop has one. + +If a \verb\for\ loop is terminated by \verb\break\, the loop control +target (list) keeps its current value. + +When \verb\break\ passes control out of a \verb\try\ statement +with a \verb\finally\ clause, that finally clause is executed +before really leaving the loop. + +\section{The {\tt continue} statement} + +\begin{verbatim} +continue_stmt: 'continue' +\end{verbatim} + +\verb\continue\ may only occur syntactically nested in a \verb\for\ +or \verb\while\ loop, not nested in a function or class definition, +and {\em not nested in a \verb\try\ statement with a \verb\finally\ +clause}. + +It continues with the next cycle of the nearest enclosing loop. + +\section{The {\tt import} statement} + +\begin{verbatim} +import_stmt: 'import' identifier (',' identifier)* + | 'from' identifier 'import' identifier (',' identifier)* + | 'from' identifier 'import' '*' +\end{verbatim} + +(XXX To be done.) + +\chapter{Compound statements} + +(XXX The semantic definitions of this chapter are still to be done.) + +\begin{verbatim} +statement: stmt_list NEWLINE | compound_stmt +compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | funcdef | classdef +suite: statement | NEWLINE INDENT statement+ DEDENT +\end{verbatim} + +\section{The {\tt if} statement} + +\begin{verbatim} +if_stmt: 'if' condition ':' suite + ('elif' condition ':' suite)* + ['else' ':' suite] +\end{verbatim} + +\section{The {\tt while} statement} + +\begin{verbatim} +while_stmt: 'while' condition ':' suite ['else' ':' suite] +\end{verbatim} + +\section{The {\tt for} statement} + +\begin{verbatim} +for_stmt: 'for' target_list 'in' condition_list ':' suite + ['else' ':' suite] +\end{verbatim} + +\section{The {\tt try} statement} + +\begin{verbatim} +try_stmt: 'try' ':' suite + ('except' condition [',' condition] ':' suite)* + ['finally' ':' suite] +\end{verbatim} + +\section{Function definitions} + +\begin{verbatim} +funcdef: 'def' identifier '(' [parameter_list] ')' ':' suite +parameter_list: parameter (',' parameter)* +parameter: identifier | '(' parameter_list ')' +\end{verbatim} + +\section{Class definitions} + +\begin{verbatim} +classdef: 'class' identifier '(' ')' [inheritance] ':' suite +inheritance: '=' identifier '(' ')' (',' identifier '(' ')')* +\end{verbatim} + +XXX Syntax for scripts, modules +XXX Syntax for interactive input, eval, exec, input + +\end{document} diff --git a/Doc/ref/ref.tex b/Doc/ref/ref.tex new file mode 100644 index 00000000000..6af7535cf18 --- /dev/null +++ b/Doc/ref/ref.tex @@ -0,0 +1,1020 @@ +% Format this file with latex. + +\documentstyle[myformat]{report} + +\title{\bf + Python Reference Manual \\ + {\em Incomplete Draft} +} + +\author{ + Guido van Rossum \\ + Dept. CST, CWI, Kruislaan 413 \\ + 1098 SJ Amsterdam, The Netherlands \\ + E-mail: {\tt guido@cwi.nl} +} + +\begin{document} + +\pagenumbering{roman} + +\maketitle + +\begin{abstract} + +\noindent +Python is a simple, yet powerful programming language that bridges the +gap between C and shell programming, and is thus ideally suited for +``throw-away programming'' +and rapid prototyping. Its syntax is put +together from constructs borrowed from a variety of other languages; +most prominent are influences from ABC, C, Modula-3 and Icon. + +The Python interpreter is easily extended with new functions and data +types implemented in C. Python is also suitable as an extension +language for highly customizable C applications such as editors or +window managers. + +Python is available for various operating systems, amongst which +several flavors of {\UNIX}, Amoeba, the Apple Macintosh O.S., +and MS-DOS. + +This reference manual describes the syntax and ``core semantics'' of +the language. It is terse, but exact and complete. The semantics of +non-essential built-in object types and of the built-in functions and +modules are described in the {\em Library Reference} document. For an +informal introduction to the language, see the {\em Tutorial} +document. + +\end{abstract} + +\pagebreak + +\tableofcontents + +\pagebreak + +\pagenumbering{arabic} + +\chapter{Introduction} + +This reference manual describes the Python programming language. +It is not intended as a tutorial. + +\chapter{Lexical analysis} + +A Python program is read by a {\em parser}. +Input to the parser is a stream of {\em tokens}, generated +by the {\em lexical analyzer}. + +\section{Line structure} + +A Python program is divided in a number of logical lines. +Statements may not straddle logical line boundaries except where +explicitly allowed by the syntax. +To this purpose, the end of a logical line +is represented by the token NEWLINE. + +\subsection{Comments} + +A comment starts with a hash character (\verb/#/) and ends at the end +of the physical line. Comments are ignored by the syntax. +A hash character in a string literal does not start a comment. + +\subsection{Line joining} + +Physical lines may be joined into logical lines using backslash +characters (\verb/\/), as follows. +If a physical line ends in a backslash that is not part of a string +literal or comment, it is joined with +the following forming a single logical line, deleting the backslash +and the following end-of-line character. More than two physical +lines may be joined together in this way. + +\subsection{Blank lines} + +A physical line that is not the continuation of the previous line +and contains only spaces, tabs and possibly a comment, is ignored +(i.e., no NEWLINE token is generated), +except that during interactive input of statements, an empty +physical line terminates a multi-line statement. + +\subsection{Indentation} + +Spaces and tabs at the beginning of a line are used to compute +the indentation level of the line, which in turn is used to determine +the grouping of statements. + +First, each tab is replaced by one to eight spaces such that the column number +of the next character is a multiple of eight (counting from zero). +The column number of the first non-space character then defines the +line's indentation. +Indentation cannot be split over multiple physical lines using +backslashes. + +The indentation levels of consecutive lines are used to generate +INDENT and DEDENT tokens, using a stack, as follows. + +Before the first line of the file is read, a single zero is pushed on +the stack; this will never be popped off again. The numbers pushed +on the stack will always be strictly increasing from bottom to top. +At the beginning of each logical line, the line's indentation level +is compared to the top of the stack. +If it is equal, nothing happens. +If it larger, it is pushed on the stack, and one INDENT token is generated. +If it is smaller, it {\em must} be one of the numbers occurring on the +stack; all numbers on the stack that are larger are popped off, +and for each number popped off a DEDENT token is generated. +At the end of the file, a DEDENT token is generated for each number +remaining on the stack that is larger than zero. + +\section{Other tokens} + +Besides NEWLINE, INDENT and DEDENT, the following categories of tokens +exist: identifiers, keywords, literals, operators, and delimiters. +Spaces and tabs are not tokens, but serve to delimit tokens. +Where ambiguity exists, a token comprises the longest possible +string that forms a legal token, when reading from left to right. + +Tokens are described using an extended regular expression notation. +This is similar to the extended BNF notation used later, except that +the notation <...> is used to give an informal description of a character, +and that spaces and tabs are not to be ignored. + +\section{Identifiers} + +Identifiers are described by the following regular expressions: + +\begin{verbatim} +identifier: (letter|'_') (letter|digit|'_')* +letter: lowercase | uppercase +lowercase: 'a'|'b'|...|'z' +uppercase: 'A'|'B'|...|'Z' +digit: '0'|'1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9' +\end{verbatim} + +Identifiers are unlimited in length. +Upper and lower case letters are different. + +\section{Keywords} + +The following tokens are used as reserved words, +or keywords of the language, +and may not be used as ordinary identifiers. +They must be spelled exactly as written here: + +{\tt + and + break + class + continue + def + del + elif + else + except + finally + for + from + if + import + in + is + not + or + pass + print + raise + return + try + while +} + +\section{Literals} + +\subsection{String literals} + +String literals are described by the following regular expressions: + +\begin{verbatim} +stringliteral: '\'' stringitem* '\'' +stringitem: stringchar | escapeseq +stringchar: +escapeseq: '\\' +\end{verbatim} + +String literals cannot span physical line boundaries. +Escape sequences in strings are actually interpreted according to almost the +same rules as used by Standard C +(XXX which should be made explicit here), +except that \verb/\E/ is equivalent to \verb/\033/, +\verb/\"/ is not recognized, +newline characters cannot be escaped, and +{\em all unrecognized escape sequences are left in the string unchanged}. +(The latter rule is useful when debugging: if an escape sequence is +mistyped, the resulting output is more easily recognized as broken. +It also helps somewhat for string literals used as regular expressions +or otherwise passed to other modules that do their own escape handling.) + +\subsection{Numeric literals} + +There are three types of numeric literals: integers, long integers, +and floating point numbers. + +Integers and long integers are described by the following regular expressions: + +\begin{verbatim} +longinteger: integer ('l'|'L') +integer: decimalinteger | octinteger | hexinteger +decimalinteger: nonzerodigit digit* | '0' +octinteger: '0' octdigit+ +hexinteger: '0' ('x'|'X') hexdigit+ + +nonzerodigit: '1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9' +octdigit: '0'|'1'|'2'|'3'|'4'|'5'|'6'|'7' +hexdigit: digit|'a'|'b'|'c'|'d'|'e'|'f'|'A'|'B'|'C'|'D'|'E'|'F' +\end{verbatim} + +Floating point numbers are described by the following regular expressions: + +\begin{verbatim} +floatnumber: [intpart] fraction [exponent] | intpart ['.'] exponent +intpart: digit+ +fraction: '.' digit+ +exponent: ('e'|'E') ['+'|'-'] digit+ +\end{verbatim} + +\section{Operators} + +The following tokens are operators: + +\begin{verbatim} ++ - * / % +<< >> & | ^ ~ +< = == > <= <> != >= +\end{verbatim} + +\section{Delimiters} + +The following tokens are delimiters: + +\begin{verbatim} +( ) [ ] { } +; , : . ` +\end{verbatim} + +The following printing ASCII characters are currently not used; +their occurrence is an unconditional error: + +\begin{verbatim} +! @ $ " ? +\end{verbatim} + +\chapter{Execution model} + +(XXX This chapter should explain the general model +of the execution of Python code and +the evaluation of expressions. +It should introduce objects, values, code blocks, scopes, name spaces, +name binding, +types, sequences, numbers, mappings, +exceptions, and other technical terms needed to make the following +chapters concise and exact.) + +\chapter{Expressions and conditions} + +(From now on, extended BNF notation will be used to describe +syntax, not lexical analysis.) +(XXX Explain the notation.) + +This chapter explains the meaning of the elements of expressions and +conditions. Conditions are a superset of expressions, and a condition +may be used where an expression is required by enclosing it in +parentheses. The only place where an unparenthesized condition +is not allowed is on the right-hand side of the assignment operator, +because this operator is the same token (\verb/'='/) as used for +compasisons. + +The comma plays a somewhat special role in Python's syntax. +It is an operator with a lower precedence than all others, but +occasionally serves other purposes as well (e.g., it has special +semantics in print statements). When a comma is accepted by the +syntax, one of the syntactic categories \verb/expression_list/ +or \verb/condition_list/ is always used. + +When (one alternative of) a syntax rule has the form + +\begin{verbatim} +name: othername +\end{verbatim} + +and no semantics are given, the semantics of this form of \verb/name/ +are the same as for \verb/othername/. + +\section{Arithmetic conversions} + +When a description of an arithmetic operator below uses the phrase +``the numeric arguments are converted to a common type'', +this both means that if either argument is not a number, a +{\tt TypeError} exception is raised, and that otherwise +the following conversions are applied: + +\begin{itemize} +\item First, if either argument is a floating point number, + the other is converted to floating point; +\item else, if either argument is a long integer, + the other is converted to long integer; +\item otherwise, both must be short integers and no conversion + is necessary. +\end{itemize} + +(Note: ``short integers'' in Python are at least 32 bits in size; +``long integers'' are arbitrary precision integers.) + +\section{Atoms} + +Atoms are the most basic elements of expressions. +Forms enclosed in reverse quotes or various types of parentheses +or braces are also categorized syntactically as atoms. +Syntax rules for atoms: + +\begin{verbatim} +atom: identifier | literal | parenth_form | string_conversion +literal: stringliteral | integer | longinteger | floatnumber +parenth_form: enclosure | list_display | dict_display +enclosure: '(' [condition_list] ')' +list_display: '[' [condition_list] ']' +dict_display: '{' [key_datum (',' key_datum)* [','] '}' +key_datum: condition ':' condition +string_conversion:'`' condition_list '`' +\end{verbatim} + +\subsection{Identifiers (Names)} + +An identifier occurring as an atom is a reference to a local, global +or built-in name binding. If a name can be assigned to anywhere in a code +block, it refers to a local name throughout that code block. +Otherwise, it refers to a global name if one exists, else to a +built-in name. + +When the name is bound to an object, evaluation of the atom +yields that object. +When it is not bound, a {\tt NameError} exception +is raised, with the identifier as string parameter. + +\subsection{Literals} + +Evaluation of a literal yields an object of the given type +(string, integer, long integer, floating point number) +with the given value. +The value may be approximated in the case of floating point literals. + +All literals correspond to immutable data types, and hence the object's +identity is less important than its value. +Multiple evaluations of the same literal (either the same occurrence +in the program text or a different occurrence) may +obtain the same object or a different object with the same value. + +(In the original implementation, all literals in the same code block +with the same type and value yield the same object.) + +\subsection{Enclosures} + +An empty enclosure yields an empty tuple object. + +An enclosed condition list yields whatever that condition list yields. + +(Note that, except for empty tuples, tuples are not formed by +enclosure in parentheses, but rather by use of the comma operator.) + +\subsection{List displays} + +A list display yields a new list object. + +If it has no condition list, the list object has no items. +Otherwise, the elements of the condition list are evaluated +from left to right and inserted in the list object in that order. + +\subsection{Dictionary displays} + +A dictionary display yields a new dictionary object. + +The key/datum pairs are evaluated from left to right to +define the entries of the dictionary: +each key object is used as a key into the dictionary to store +the corresponding datum pair. + +Key objects must be strings, otherwise a {\tt TypeError} +exception is raised. +Clashes between keys are not detected; the last datum stored for a given +key value prevails. + +\subsection{String conversions} + +A string conversion evaluates the contained condition list and converts the +resulting object into a string according to rules specific to its type. + +If the object is a string, a number, \verb/None/, or a tuple, list or +dictionary containing only objects whose type is in this list, +the resulting +string is a valid Python expression which can be passed to the +built-in function \verb/eval()/ to yield an expression with the +same value (or an approximation, if floating point numbers are +involved). + +(In particular, converting a string adds quotes around it and converts +``funny'' characters to escape sequences that are safe to print.) + +It is illegal to attempt to convert recursive objects (e.g., +lists or dictionaries that -- directly or indirectly -- contain a reference +to themselves.) + +\section{Primaries} + +Primaries represent the most tightly bound operations of the language. +Their syntax is: + +\begin{verbatim} +primary: atom | attributeref | call | subscription | slicing +attributeref: primary '.' identifier +call: primary '(' [condition_list] ')' +subscription: primary '[' condition ']' +slicing: primary '[' [condition] ':' [condition] ']' +\end{verbatim} + +\subsection{Attribute references} + +\subsection{Calls} + +\subsection{Subscriptions} + +\subsection{Slicings} + +\section{Factors} + +Factors represent the unary numeric operators. +Their syntax is: + +\begin{verbatim} +factor: primary | '-' factor | '+' factor | '~' factor +\end{verbatim} + +The unary \verb/'-'/ operator yields the negative of its numeric argument. + +The unary \verb/'+'/ operator yields its numeric argument unchanged. + +The unary \verb/'~'/ operator yields the bit-wise negation of its +integral numerical argument. + +In all three cases, if the argument does not have the proper type, +a {\tt TypeError} exception is raised. + +\section{Terms} + +Terms represent the most tightly binding binary operators: + +\begin{verbatim} +term: factor | term '*' factor | term '/' factor | term '%' factor +\end{verbatim} + +The \verb/'*'/ operator yields the product of its arguments. +The arguments must either both be numbers, or one argument must be +a (short) integer and the other must be a string. +In the former case, the numbers are converted to a common type +and then multiplied together. +In the latter case, string repetition is performed; a negative +repetition factor yields the empty string. + +The \verb|'/'| operator yields the quotient of its arguments. +The numeric arguments are first converted to a common type. +(Short or long) integer division yields an integer of the same type, +truncating towards zero. +Division by zero raises a {\tt RuntimeError} exception. + +The \verb|'%'| operator yields the remainder from the division +of the first argument by the second. +The numeric arguments are first converted to a common type. +The outcome of $x % y$ is defined as $x - y*trunc(x/y)$. +A zero right argument raises a {\tt RuntimeError} exception. +The arguments may be floating point numbers, e.g., +$3.14 % 0.7$ equals $0.34$. + +\section{Arithmetic expressions} + +\begin{verbatim} +arith_expr: term | arith_expr '+' term | arith_expr '-' term +\end{verbatim} + +The \verb|'+'| operator yields the sum of its arguments. +The arguments must either both be numbers, or both strings. +In the former case, the numbers are converted to a common type +and then added together. +In the latter case, the strings are concatenated directly, +without inserting a space. + +The \verb|'-'| operator yields the difference of its arguments. +The numeric arguments are first converted to a common type. + +\section{Shift expressions} + +\begin{verbatim} +shift_expr: arith_expr | shift_expr '<<' arith_expr | shift_expr '>>' arith_expr +\end{verbatim} + +These operators accept short integers as arguments only. +They shift their left argument to the left or right by the number of bits +given by the right argument. Shifts are ``logical'', e.g., bits shifted +out on one end are lost, and bits shifted in are zero; +negative numbers are shifted as if they were unsigned in C. +Negative shift counts and shift counts greater than {\em or equal to} +the word size yield undefined results. + +\section{Bitwise AND expressions} + +\begin{verbatim} +and_expr: shift_expr | and_expr '&' shift_expr +\end{verbatim} + +This operator yields the bitwise AND of its arguments, +which must be short integers. + +\section{Bitwise XOR expressions} + +\begin{verbatim} +xor_expr: and_expr | xor_expr '^' and_expr +\end{verbatim} + +This operator yields the bitwise exclusive OR of its arguments, +which must be short integers. + +\section{Bitwise OR expressions} + +\begin{verbatim} +or_expr: xor_expr | or_expr '|' xor_expr +\end{verbatim} + +This operator yields the bitwise OR of its arguments, +which must be short integers. + +\section{Expressions and expression lists} + +\begin{verbatim} +expression: or_expression +expr_list: expression (',' expression)* [','] +\end{verbatim} + +An expression list containing at least one comma yields a new tuple. +The length of the tuple is the number of expressions in the list. +The expressions are evaluated from left to right. + +The trailing comma is required only to create a single tuple; +it is optional in all other cases (a single expression without +a trailing comma doesn't create a tuple, but rather yields the +value of that expression). + +To create an empty tuple, use an empty pair of parentheses: \verb/()/. + +\section{Comparisons} + +\begin{verbatim} +comparison: expression (comp_operator expression)* +comp_operator: '<'|'>'|'='|'=='|'>='|'<='|'<>'|'!='|['not'] 'in'|is' ['not'] +\end{verbatim} + +Comparisons yield integer value: 1 for true, 0 for false. + +Comparisons can be chained arbitrarily, +e.g., $x < y <= z$ is equivalent to +$x < y$ {\tt and} $y <= z$, except that $y$ is evaluated only once +(but in both cases $z$ is not evaluated at all when $x < y$ is +found to be false). + +Formally, $e_0 op_1 e_1 op_2 e_2 ...e_{n-1} op_n e_n$ is equivalent to +$e_0 op_1 e_1$ {\tt and} $e_1 op_2 e_2$ {\tt and} ... {\tt and} +$e_{n-1} op_n e_n$, except that each expression is evaluated at most once. + +Note that $e_0 op_1 e_1 op_2 e_2$ does not imply any kind of comparison +between $e_0$ and $e_2$, e.g., $x < y > z$ is perfectly legal. + +For the benefit of C programmers, +the comparison operators \verb/=/ and \verb/==/ are equivalent, +and so are \verb/<>/ and \verb/!=/. +Use of the C variants is discouraged. + +The operators {\tt '<', '>', '=', '>=', '<='}, and {\tt '<>'} compare +the values of two objects. The objects needn't have the same type. +If both are numbers, they are compared to a common type. +Otherwise, objects of different types {\em always} compare unequal, +and are ordered consistently but arbitrarily, except that +the value \verb\None\ compares smaller than the values of any other type. + +(This unusual +definition of comparison is done to simplify the definition of +operations like sorting and the \verb/in/ and \verb/not in/ operators.) + +Comparison of objects of the same type depends on the type: + +\begin{itemize} +\item Numbers are compared arithmetically. +\item Strings are compared lexicographically using the numeric + equivalents (the result of the built-in function ord()) + of their characters. +\item Tuples and lists are compared lexicographically + using comparison of corresponding items. +\item Dictionaries compare unequal unless they are the same object; + the choice whether one dictionary object is considered smaller + or larger than another one is made arbitrarily but + consistently within one execution of a program. +\item The latter rule is also used for most other built-in types. +\end{itemize} + +The operators \verb\in\ and \verb\not in\ test for sequence membership: +if $y$ is a sequence, $x {\tt in} y$ is true if and only if there exists +an index $i$ such that $x = y_i$. +$x {\tt not in} y$ yields the inverse truth value. +The exception {\tt TypeError} is raised when $y$ is not a sequence, +or when $y$ is a string and $x$ is not a string of length one. + +The operators \verb\is\ and \verb\is not\ compare object identity: +$x {\tt is} y$ is true if and only if $x$ and $y$ are the same object. +$x {\tt is not} y$ yields the inverse truth value. + +\section{Boolean operators} + +\begin{verbatim} +condition: or_test +or_test: and_test | or_test 'or' and_test +and_test: not_test | and_test 'and' not_test +not_test: comparison | 'not' not_test +\end{verbatim} + +In the context of Boolean operators, and also when conditions are +used by control flow statements, the following values are interpreted +as false: None, numeric zero of all types, empty sequences (strings, +tuples and lists), and empty mappings (dictionaries). +All other values are interpreted as true. + +The operator \verb\not\ yields 1 if its argument is false, 0 otherwise. + +The condition $x {\tt and} y$ first evaluates $x$; if $x$ is false, +$x$ is returned; otherwise, $y$ is evaluated and returned. + +The condition $x {\tt or} y$ first evaluates $x$; if $x$ is true, +$x$ is returned; otherwise, $y$ is evaluated and returned. + +(Note that \verb\and\ and \verb\or\ do not restrict the value and type +they return to 0 and 1, but rather return the last evaluated argument. +This is sometimes useful, e.g., if $s$ is a string, which should be +replaced by a default value if it is empty, $s {\tt or} 'foo'$ +returns the desired value. Because \verb\not\ has to invent a value +anyway, it does not bother to return a value of the same type as its +argument, so \verb\not 'foo'\ yields $0$, not $''$.) + +\chapter{Simple statements} + +Simple statements are comprised within a single logical line. +Several simple statements may occor on a single line separated +by semicolons. The syntax for simple statements is: + +\begin{verbatim} +stmt_list: simple_stmt (';' simple_stmt)* [';'] +simple_stmt: expression_stmt + | assignment + | pass_stmt + | del_stmt + | print_stmt + | return_stmt + | raise_stmt + | break_stmt + | continue_stmt + | import_stmt +\end{verbatim} + +\section{Expression statements} + +\begin{verbatim} +expression_stmt: expression_list +\end{verbatim} + +An expression statement evaluates the expression list (which may +be a single expression). +If the value is not \verb\None\, it is converted to a string +using the rules for string conversions, and the resulting string +is written to standard output on a line by itself. + +(The exception for \verb\None\ is made so that procedure calls, +which are syntactically equivalent to expressions, +do not cause any output.) + +\section{Assignments} + +\begin{verbatim} +assignment: target_list ('=' target_list)* '=' expression_list +target_list: target (',' target)* [','] +target: identifier | '(' target_list ')' | '[' target_list ']' + | attributeref | subscription | slicing +\end{verbatim} + +(See the section on primaries for the definition of the last +three symbols.) + +An assignment evaluates the expression list (remember that this can +be a single expression or a comma-separated list, +the latter yielding a tuple) +and assigns the single resulting object to each of the target lists, +from left to right. + +Assignment is defined recursively depending on the type of the +target. Where assignment is to part of a mutable object +(through an attribute reference, subscription or slicing), +the mutable object must ultimately perform the +assignment and decide about its validity, raising an exception +if the assignment is unacceptable. The rules observed by +various types and the exceptions raised are given with the +definition of the object types (some of which are defined +in the library reference). + +Assignment of an object to a target list is recursively +defined as follows. + +\begin{itemize} +\item +If the target list contains no commas (except in nested constructs): +the object is assigned to the single target contained in the list. + +\item +If the target list contains commas (that are not in nested constructs): +the object must be a tuple with as many items +as the list contains targets, and the items are assigned, from left +to right, to the corresponding targets. + +\end{itemize} + +Assignment of an object to a (non-list) +target is recursively defined as follows. + +\begin{itemize} + +\item +If the target is an identifier (name): +the object is bound to that name +in the current local scope. Any previous binding of the same name +is undone. + +\item +If the target is a target list enclosed in parentheses: +the object is assigned to that target list. + +\item +If the target is a target list enclosed in square brackets: +the object must be a list with as many items +as the target list contains targets, +and the list's items are assigned, from left to right, +to the corresponding targets. + +\item +If the target is an attribute reference: +The primary expression in the reference is evaluated. +It should yield an object with assignable attributes; +if this is not the case, a {\tt TypeError} exception is raised. +That object is then asked to assign the assigned object +to the given attribute; if it cannot perform the assignment, +it raises an exception. + +\item +If the target is a subscription: +The primary expression in the reference is evaluated. +It should yield either a mutable sequence object or a mapping +(dictionary) object. +Next, the subscript expression is evaluated. + +If the primary is a sequence object, the subscript must yield a +nonnegative integer smaller than the sequence's length, +and the sequence is asked to assign the assigned object +to its item with that index. + +If the primary is a mapping object, the subscript must have a +type compatible with the mapping's key type, +and the mapping is then asked to to create a key/datum pair +which maps the subscript to the assigned object. + +Various exceptions can be raised. + +\item +If the target is a slicing: +The primary expression in the reference is evaluated. +It should yield a mutable sequence object (currently only lists). +The assigned object should be a sequence object of the same type. +Next, the lower and upper bound expressions are evaluated, +insofar they are present; defaults are zero and the sequence's length. +The bounds should evaluate to (small) integers. +If either bound is negative, the sequence's length is added to it (once). +The resulting bounds are clipped to lie between zero +and the sequence's length, inclusive. +(XXX Shouldn't this description be with expressions?) +Finally, the sequence object is asked to replace the items +indicated by the slice with the items of the assigned sequence. +This may change the sequence's length, if it allows it. + +\end{itemize} + +(In the original implementation, the syntax for targets is taken +to be the same as for expressions, and invalid syntax is rejected +during the code generation phase, causing less detailed error +messages.) + +\section{The {\tt pass} statement} + +\begin{verbatim} +pass_stmt: 'pass' +\end{verbatim} + +{\tt pass} is a null operation -- when it is executed, +nothing happens. + +\section{The {\tt del} statement} + +\begin{verbatim} +del_stmt: 'del' target_list +\end{verbatim} + +Deletion is recursively defined similar to assignment. + +(XXX Rather that spelling it out in full details, +here are some hints.) + +Deletion of a target list recursively deletes each target, +from left to right. + +Deletion of a name removes the binding of that name (which must exist) +from the local scope. + +Deletion of attribute references, subscriptions and slicings +is passed to the primary object involved; deletion of a slicing +is in general equivalent to assignment of an empty slice of the +right type (but even this is determined by the sliced object). + +\section{The {\tt print} statement} + +\begin{verbatim} +print_stmt: 'print' [ condition (',' condition)* [','] ] +\end{verbatim} + +{\tt print} evaluates each condition in turn and writes the resulting +object to standard output (see below). +If an object is not a string, it is first converted to +a string using the rules for string conversions. +The (resulting or original) string is then written. +A space is written before each object is (converted and) written, +unless the output system believes it is positioned at the beginning +of a line. This is the case: (1) when no characters have been written +to standard output; or (2) when the last character written to +standard output is \verb/'\n'/; +or (3) when the last I/O operation +on standard output was not a \verb\print\ statement. + +Finally, +a \verb/'\n'/ character is written at the end, +unless the \verb\print\ statement ends with a comma. +This is the only action if the statement contains just the keyword +\verb\print\. + +Standard output is defined as the file object named \verb\stdout\ +in the built-in module \verb\sys\. If no such object exists, +or if it is not a writable file, a {\tt RuntimeError} exception is raised. +(The original implementation attempts to write to the system's original +standard output instead, but this is not safe, and should be fixed.) + +\section{The {\tt return} statement} + +\begin{verbatim} +return_stmt: 'return' [condition_list] +\end{verbatim} + +\verb\return\ may only occur syntactically nested in a function +definition, not within a nested class definition. + +If a condition list is present, it is evaluated, else \verb\None\ +is substituted. + +\verb\return\ leaves the current function call with the condition +list (or \verb\None\) as return value. + +When \verb\return\ passes control out of a \verb\try\ statement +with a \verb\finally\ clause, that finally clause is executed +before really leaving the function. +(XXX This should be made more exact, a la Modula-3.) + +\section{The {\tt raise} statement} + +\begin{verbatim} +raise_stmt: 'raise' condition [',' condition] +\end{verbatim} + +\verb\raise\ evaluates its first condition, which must yield +a string object. If there is a second condition, this is evaluated, +else \verb\None\ is substituted. + +It then raises the exception identified by the first object, +with the second one (or \verb\None\) as its parameter. + +\section{The {\tt break} statement} + +\begin{verbatim} +break_stmt: 'break' +\end{verbatim} + +\verb\break\ may only occur syntactically nested in a \verb\for\ +or \verb\while\ loop, not nested in a function or class definition. + +It terminates the neares enclosing loop, skipping the optional +\verb\else\ clause if the loop has one. + +If a \verb\for\ loop is terminated by \verb\break\, the loop control +target (list) keeps its current value. + +When \verb\break\ passes control out of a \verb\try\ statement +with a \verb\finally\ clause, that finally clause is executed +before really leaving the loop. + +\section{The {\tt continue} statement} + +\begin{verbatim} +continue_stmt: 'continue' +\end{verbatim} + +\verb\continue\ may only occur syntactically nested in a \verb\for\ +or \verb\while\ loop, not nested in a function or class definition, +and {\em not nested in a \verb\try\ statement with a \verb\finally\ +clause}. + +It continues with the next cycle of the nearest enclosing loop. + +\section{The {\tt import} statement} + +\begin{verbatim} +import_stmt: 'import' identifier (',' identifier)* + | 'from' identifier 'import' identifier (',' identifier)* + | 'from' identifier 'import' '*' +\end{verbatim} + +(XXX To be done.) + +\chapter{Compound statements} + +(XXX The semantic definitions of this chapter are still to be done.) + +\begin{verbatim} +statement: stmt_list NEWLINE | compound_stmt +compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | funcdef | classdef +suite: statement | NEWLINE INDENT statement+ DEDENT +\end{verbatim} + +\section{The {\tt if} statement} + +\begin{verbatim} +if_stmt: 'if' condition ':' suite + ('elif' condition ':' suite)* + ['else' ':' suite] +\end{verbatim} + +\section{The {\tt while} statement} + +\begin{verbatim} +while_stmt: 'while' condition ':' suite ['else' ':' suite] +\end{verbatim} + +\section{The {\tt for} statement} + +\begin{verbatim} +for_stmt: 'for' target_list 'in' condition_list ':' suite + ['else' ':' suite] +\end{verbatim} + +\section{The {\tt try} statement} + +\begin{verbatim} +try_stmt: 'try' ':' suite + ('except' condition [',' condition] ':' suite)* + ['finally' ':' suite] +\end{verbatim} + +\section{Function definitions} + +\begin{verbatim} +funcdef: 'def' identifier '(' [parameter_list] ')' ':' suite +parameter_list: parameter (',' parameter)* +parameter: identifier | '(' parameter_list ')' +\end{verbatim} + +\section{Class definitions} + +\begin{verbatim} +classdef: 'class' identifier '(' ')' [inheritance] ':' suite +inheritance: '=' identifier '(' ')' (',' identifier '(' ')')* +\end{verbatim} + +XXX Syntax for scripts, modules +XXX Syntax for interactive input, eval, exec, input + +\end{document}