mirror of https://github.com/python/cpython
Cleaned up some remaining markup nits.
Andrew: In description of (?iLmsx), you say it matches the empty string and sets the corresponding flag. Is this correct? Or does it only set the flag?
This commit is contained in:
Fred Drake
parent
8fab8cf211
commit
013ad9869e
|
|
@ -265,7 +265,7 @@ The module defines the following functions and constants, and an exception:
|
|||
|
||||
\setindexsubitem{(in module re)}
|
||||
|
||||
\begin{funcdesc}{compile}{pattern\optional{\, flags}}
|
||||
\begin{funcdesc}{compile}{pattern\optional{, flags}}
|
||||
Compile a regular expression pattern into a regular expression
|
||||
object, which can be used for matching using its \function{match()} and
|
||||
\function{search()} methods, described below.
|
||||
|
|
@ -274,23 +274,20 @@ The module defines the following functions and constants, and an exception:
|
|||
\var{flags} value. Values can be any of the following variables,
|
||||
combined using bitwise OR (the \code{|} operator).
|
||||
|
||||
\begin{description}
|
||||
|
||||
% The use of \quad in the item labels is ugly but adds enough space
|
||||
% to the label that it doesn't get visually run-in with the text.
|
||||
|
||||
\item[\constant{I} or \constant{IGNORECASE} or \code{(?i)}\quad]
|
||||
|
||||
\begin{datadesc}{I}
|
||||
\dataline{IGNORECASE}
|
||||
Perform case-insensitive matching; expressions like \code{[A-Z]} will match
|
||||
lowercase letters, too. This is not affected by the current locale.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{L} or \constant{LOCALE} or \constant{(?L)}\quad]
|
||||
|
||||
\begin{datadesc}{L}
|
||||
\dataline{LOCALE}
|
||||
Make \code{\e w}, \code{\e W}, \code{\e b},
|
||||
\code{\e B}, dependent on the current locale.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{M} or \constant{MULTILINE} or \constant{(?m)}\quad]
|
||||
|
||||
\begin{datadesc}{M}
|
||||
\dataline{MULTILINE}
|
||||
When specified, the pattern character \code{\^} matches at the
|
||||
beginning of the string and at the beginning of each line
|
||||
(immediately following each newline); and the pattern character
|
||||
|
|
@ -299,30 +296,32 @@ beginning of the string and at the beginning of each line
|
|||
By default, \code{\^} matches only at the beginning of the string, and
|
||||
\code{\$} only at the end of the string and immediately before the
|
||||
newline (if any) at the end of the string.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{S} or \constant{DOTALL} or \constant{(?s)}\quad]
|
||||
|
||||
\begin{datadesc}{S}
|
||||
\dataline{DOTALL}
|
||||
Make the \code{.} special character any character at all, including a
|
||||
newline; without this flag, \code{.} will match anything \emph{except}
|
||||
a newline.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{X} or \constant{VERBOSE} or \constant{(?x)}\quad]
|
||||
|
||||
\begin{datadesc}{X}
|
||||
\dataline{VERBOSE}
|
||||
Ignore whitespace within the pattern
|
||||
except when in a character class or preceded by an unescaped
|
||||
backslash, and, when a line contains a \code{\#} neither in a character
|
||||
class or preceded by an unescaped backslash, all characters from the
|
||||
leftmost such \code{\#} through the end of the line are ignored.
|
||||
\end{datadesc}
|
||||
|
||||
\end{description}
|
||||
|
||||
The sequence
|
||||
%
|
||||
|
||||
\begin{verbatim}
|
||||
prog = re.compile(pat)
|
||||
result = prog.match(str)
|
||||
\end{verbatim}
|
||||
%
|
||||
|
||||
is equivalent to
|
||||
|
||||
\begin{verbatim}
|
||||
|
|
@ -343,7 +342,7 @@ expression will be used several times in a single program.
|
|||
regular expression metacharacters in it.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{match}{pattern\, string\optional{\, flags}}
|
||||
\begin{funcdesc}{match}{pattern, string\optional{, flags}}
|
||||
If zero or more characters at the beginning of \var{string} match
|
||||
the regular expression \var{pattern}, return a corresponding
|
||||
\class{MatchObject} instance. Return \code{None} if the string does not
|
||||
|
|
@ -351,7 +350,7 @@ expression will be used several times in a single program.
|
|||
match.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{search}{pattern\, string\optional{\, flags}}
|
||||
\begin{funcdesc}{search}{pattern, string\optional{, flags}}
|
||||
Scan through \var{string} looking for a location where the regular
|
||||
expression \var{pattern} produces a match, and return a
|
||||
corresponding \class{MatchObject} instance.
|
||||
|
|
@ -360,7 +359,7 @@ expression will be used several times in a single program.
|
|||
different from finding a zero-length match at some point in the string.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{split}{pattern\, string\, \optional{, maxsplit=0}}
|
||||
\begin{funcdesc}{split}{pattern, string, \optional{, maxsplit\code{ = 0}}}
|
||||
Split \var{string} by the occurrences of \var{pattern}. If
|
||||
capturing parentheses are used in pattern, then occurrences of
|
||||
patterns or subpatterns are also returned.
|
||||
|
|
@ -383,7 +382,7 @@ expression will be used several times in a single program.
|
|||
the old \function{regsub.split()} and \function{regsub.splitx()}.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{sub}{pattern\, repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{sub}{pattern, repl, string\optional{, count\code{ = 0}}}
|
||||
Return the string obtained by replacing the leftmost non-overlapping
|
||||
occurrences of \var{pattern} in \var{string} by the replacement
|
||||
\var{repl}. If the pattern isn't found, \var{string} is returned
|
||||
|
|
@ -404,20 +403,17 @@ The pattern may be a string or a
|
|||
regex object; if you need to specify
|
||||
regular expression flags, you must use a regex object, or use
|
||||
embedded modifiers in a pattern; e.g.
|
||||
|
||||
\begin{verbatim}
|
||||
sub("(?i)b+", "x", "bbbb BBBB") returns 'x x'.
|
||||
\end{verbatim}
|
||||
\samp{sub("(?i)b+", "x", "bbbb BBBB")} returns \code{'x x'}.
|
||||
|
||||
The optional argument \var{count} is the maximum number of pattern
|
||||
occurrences to be replaced; count must be a non-negative integer, and
|
||||
the default value of 0 means to replace all occurrences.
|
||||
|
||||
Empty matches for the pattern are replaced only when not adjacent to a
|
||||
previous match, so \code{sub('x*', '-', 'abc')} returns '-a-b-c-'.
|
||||
previous match, so \samp{sub('x*', '-', 'abc')} returns \code{'-a-b-c-'}.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{subn}{pattern\, repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{subn}{pattern, repl, string\optional{, count\code{ = 0}}}
|
||||
Perform the same operation as \function{sub()}, but return a tuple
|
||||
\code{(\var{new_string}, \var{number_of_subs_made})}.
|
||||
\end{funcdesc}
|
||||
|
|
@ -425,8 +421,8 @@ Perform the same operation as \function{sub()}, but return a tuple
|
|||
\begin{excdesc}{error}
|
||||
Exception raised when a string passed to one of the functions here
|
||||
is not a valid regular expression (e.g., unmatched parentheses) or
|
||||
when some other error occurs during compilation or matching. (It is
|
||||
never an error if a string contains no match for a pattern.)
|
||||
when some other error occurs during compilation or matching. It is
|
||||
never an error if a string contains no match for a pattern.
|
||||
\end{excdesc}
|
||||
|
||||
\subsection{Regular Expression Objects}
|
||||
|
|
@ -434,7 +430,7 @@ Compiled regular expression objects support the following methods and
|
|||
attributes:
|
||||
|
||||
\setindexsubitem{(re method)}
|
||||
\begin{funcdesc}{match}{string\optional{\, pos}\optional{\, endpos}}
|
||||
\begin{funcdesc}{match}{string\optional{, pos}\optional{, endpos}}
|
||||
If zero or more characters at the beginning of \var{string} match
|
||||
this regular expression, return a corresponding
|
||||
\class{MatchObject} instance. Return \code{None} if the string does not
|
||||
|
|
@ -452,7 +448,7 @@ attributes:
|
|||
searched for a match.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{search}{string\optional{\, pos}\optional{\, endpos}}
|
||||
\begin{funcdesc}{search}{string\optional{, pos}\optional{, endpos}}
|
||||
Scan through \var{string} looking for a location where this regular
|
||||
expression produces a match. Return \code{None} if no
|
||||
position in the string matches the pattern; note that this is
|
||||
|
|
@ -462,28 +458,28 @@ attributes:
|
|||
meaning as for the \method{match()} method.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{split}{string\, \optional{, maxsplit=0}}
|
||||
\begin{funcdesc}{split}{string, \optional{, maxsplit\code{ = 0}}}
|
||||
Identical to the \function{split()} function, using the compiled pattern.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{sub}{repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{sub}{repl, string\optional{, count\code{ = 0}}}
|
||||
Identical to the \function{sub()} function, using the compiled pattern.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{subn}{repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{subn}{repl, string\optional{, count\code{ = 0}}}
|
||||
Identical to the \function{subn()} function, using the compiled pattern.
|
||||
\end{funcdesc}
|
||||
|
||||
\setindexsubitem{(regex attribute)}
|
||||
|
||||
\begin{datadesc}{flags}
|
||||
The flags argument used when the regex object was compiled, or 0 if no
|
||||
flags were provided.
|
||||
The flags argument used when the regex object was compiled, or
|
||||
\code{0} if no flags were provided.
|
||||
\end{datadesc}
|
||||
|
||||
\begin{datadesc}{groupindex}
|
||||
A dictionary mapping any symbolic group names (defined by
|
||||
\code{?P<\var{id}>}) to group numbers. The dictionary is empty if no
|
||||
A dictionary mapping any symbolic group names defined by
|
||||
\code{(?P<\var{id}>)} to group numbers. The dictionary is empty if no
|
||||
symbolic groups were used in the pattern.
|
||||
\end{datadesc}
|
||||
|
||||
|
|
@ -531,9 +527,7 @@ singleton tuple is returned in such cases.)
|
|||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{start}{\optional{group}}
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{end}{\optional{group}}
|
||||
\funcline{end}{\optional{group}}
|
||||
Return the indices of the start and end of the substring
|
||||
matched by \var{group}; \var{group} defaults to zero (meaning the whole
|
||||
matched substring).
|
||||
|
|
|
|||
|
|
@ -265,7 +265,7 @@ The module defines the following functions and constants, and an exception:
|
|||
|
||||
\setindexsubitem{(in module re)}
|
||||
|
||||
\begin{funcdesc}{compile}{pattern\optional{\, flags}}
|
||||
\begin{funcdesc}{compile}{pattern\optional{, flags}}
|
||||
Compile a regular expression pattern into a regular expression
|
||||
object, which can be used for matching using its \function{match()} and
|
||||
\function{search()} methods, described below.
|
||||
|
|
@ -274,23 +274,20 @@ The module defines the following functions and constants, and an exception:
|
|||
\var{flags} value. Values can be any of the following variables,
|
||||
combined using bitwise OR (the \code{|} operator).
|
||||
|
||||
\begin{description}
|
||||
|
||||
% The use of \quad in the item labels is ugly but adds enough space
|
||||
% to the label that it doesn't get visually run-in with the text.
|
||||
|
||||
\item[\constant{I} or \constant{IGNORECASE} or \code{(?i)}\quad]
|
||||
|
||||
\begin{datadesc}{I}
|
||||
\dataline{IGNORECASE}
|
||||
Perform case-insensitive matching; expressions like \code{[A-Z]} will match
|
||||
lowercase letters, too. This is not affected by the current locale.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{L} or \constant{LOCALE} or \constant{(?L)}\quad]
|
||||
|
||||
\begin{datadesc}{L}
|
||||
\dataline{LOCALE}
|
||||
Make \code{\e w}, \code{\e W}, \code{\e b},
|
||||
\code{\e B}, dependent on the current locale.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{M} or \constant{MULTILINE} or \constant{(?m)}\quad]
|
||||
|
||||
\begin{datadesc}{M}
|
||||
\dataline{MULTILINE}
|
||||
When specified, the pattern character \code{\^} matches at the
|
||||
beginning of the string and at the beginning of each line
|
||||
(immediately following each newline); and the pattern character
|
||||
|
|
@ -299,30 +296,32 @@ beginning of the string and at the beginning of each line
|
|||
By default, \code{\^} matches only at the beginning of the string, and
|
||||
\code{\$} only at the end of the string and immediately before the
|
||||
newline (if any) at the end of the string.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{S} or \constant{DOTALL} or \constant{(?s)}\quad]
|
||||
|
||||
\begin{datadesc}{S}
|
||||
\dataline{DOTALL}
|
||||
Make the \code{.} special character any character at all, including a
|
||||
newline; without this flag, \code{.} will match anything \emph{except}
|
||||
a newline.
|
||||
\end{datadesc}
|
||||
|
||||
\item[\constant{X} or \constant{VERBOSE} or \constant{(?x)}\quad]
|
||||
|
||||
\begin{datadesc}{X}
|
||||
\dataline{VERBOSE}
|
||||
Ignore whitespace within the pattern
|
||||
except when in a character class or preceded by an unescaped
|
||||
backslash, and, when a line contains a \code{\#} neither in a character
|
||||
class or preceded by an unescaped backslash, all characters from the
|
||||
leftmost such \code{\#} through the end of the line are ignored.
|
||||
\end{datadesc}
|
||||
|
||||
\end{description}
|
||||
|
||||
The sequence
|
||||
%
|
||||
|
||||
\begin{verbatim}
|
||||
prog = re.compile(pat)
|
||||
result = prog.match(str)
|
||||
\end{verbatim}
|
||||
%
|
||||
|
||||
is equivalent to
|
||||
|
||||
\begin{verbatim}
|
||||
|
|
@ -343,7 +342,7 @@ expression will be used several times in a single program.
|
|||
regular expression metacharacters in it.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{match}{pattern\, string\optional{\, flags}}
|
||||
\begin{funcdesc}{match}{pattern, string\optional{, flags}}
|
||||
If zero or more characters at the beginning of \var{string} match
|
||||
the regular expression \var{pattern}, return a corresponding
|
||||
\class{MatchObject} instance. Return \code{None} if the string does not
|
||||
|
|
@ -351,7 +350,7 @@ expression will be used several times in a single program.
|
|||
match.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{search}{pattern\, string\optional{\, flags}}
|
||||
\begin{funcdesc}{search}{pattern, string\optional{, flags}}
|
||||
Scan through \var{string} looking for a location where the regular
|
||||
expression \var{pattern} produces a match, and return a
|
||||
corresponding \class{MatchObject} instance.
|
||||
|
|
@ -360,7 +359,7 @@ expression will be used several times in a single program.
|
|||
different from finding a zero-length match at some point in the string.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{split}{pattern\, string\, \optional{, maxsplit=0}}
|
||||
\begin{funcdesc}{split}{pattern, string, \optional{, maxsplit\code{ = 0}}}
|
||||
Split \var{string} by the occurrences of \var{pattern}. If
|
||||
capturing parentheses are used in pattern, then occurrences of
|
||||
patterns or subpatterns are also returned.
|
||||
|
|
@ -383,7 +382,7 @@ expression will be used several times in a single program.
|
|||
the old \function{regsub.split()} and \function{regsub.splitx()}.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{sub}{pattern\, repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{sub}{pattern, repl, string\optional{, count\code{ = 0}}}
|
||||
Return the string obtained by replacing the leftmost non-overlapping
|
||||
occurrences of \var{pattern} in \var{string} by the replacement
|
||||
\var{repl}. If the pattern isn't found, \var{string} is returned
|
||||
|
|
@ -404,20 +403,17 @@ The pattern may be a string or a
|
|||
regex object; if you need to specify
|
||||
regular expression flags, you must use a regex object, or use
|
||||
embedded modifiers in a pattern; e.g.
|
||||
|
||||
\begin{verbatim}
|
||||
sub("(?i)b+", "x", "bbbb BBBB") returns 'x x'.
|
||||
\end{verbatim}
|
||||
\samp{sub("(?i)b+", "x", "bbbb BBBB")} returns \code{'x x'}.
|
||||
|
||||
The optional argument \var{count} is the maximum number of pattern
|
||||
occurrences to be replaced; count must be a non-negative integer, and
|
||||
the default value of 0 means to replace all occurrences.
|
||||
|
||||
Empty matches for the pattern are replaced only when not adjacent to a
|
||||
previous match, so \code{sub('x*', '-', 'abc')} returns '-a-b-c-'.
|
||||
previous match, so \samp{sub('x*', '-', 'abc')} returns \code{'-a-b-c-'}.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{subn}{pattern\, repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{subn}{pattern, repl, string\optional{, count\code{ = 0}}}
|
||||
Perform the same operation as \function{sub()}, but return a tuple
|
||||
\code{(\var{new_string}, \var{number_of_subs_made})}.
|
||||
\end{funcdesc}
|
||||
|
|
@ -425,8 +421,8 @@ Perform the same operation as \function{sub()}, but return a tuple
|
|||
\begin{excdesc}{error}
|
||||
Exception raised when a string passed to one of the functions here
|
||||
is not a valid regular expression (e.g., unmatched parentheses) or
|
||||
when some other error occurs during compilation or matching. (It is
|
||||
never an error if a string contains no match for a pattern.)
|
||||
when some other error occurs during compilation or matching. It is
|
||||
never an error if a string contains no match for a pattern.
|
||||
\end{excdesc}
|
||||
|
||||
\subsection{Regular Expression Objects}
|
||||
|
|
@ -434,7 +430,7 @@ Compiled regular expression objects support the following methods and
|
|||
attributes:
|
||||
|
||||
\setindexsubitem{(re method)}
|
||||
\begin{funcdesc}{match}{string\optional{\, pos}\optional{\, endpos}}
|
||||
\begin{funcdesc}{match}{string\optional{, pos}\optional{, endpos}}
|
||||
If zero or more characters at the beginning of \var{string} match
|
||||
this regular expression, return a corresponding
|
||||
\class{MatchObject} instance. Return \code{None} if the string does not
|
||||
|
|
@ -452,7 +448,7 @@ attributes:
|
|||
searched for a match.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{search}{string\optional{\, pos}\optional{\, endpos}}
|
||||
\begin{funcdesc}{search}{string\optional{, pos}\optional{, endpos}}
|
||||
Scan through \var{string} looking for a location where this regular
|
||||
expression produces a match. Return \code{None} if no
|
||||
position in the string matches the pattern; note that this is
|
||||
|
|
@ -462,28 +458,28 @@ attributes:
|
|||
meaning as for the \method{match()} method.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{split}{string\, \optional{, maxsplit=0}}
|
||||
\begin{funcdesc}{split}{string, \optional{, maxsplit\code{ = 0}}}
|
||||
Identical to the \function{split()} function, using the compiled pattern.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{sub}{repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{sub}{repl, string\optional{, count\code{ = 0}}}
|
||||
Identical to the \function{sub()} function, using the compiled pattern.
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{subn}{repl\, string\optional{, count=0}}
|
||||
\begin{funcdesc}{subn}{repl, string\optional{, count\code{ = 0}}}
|
||||
Identical to the \function{subn()} function, using the compiled pattern.
|
||||
\end{funcdesc}
|
||||
|
||||
\setindexsubitem{(regex attribute)}
|
||||
|
||||
\begin{datadesc}{flags}
|
||||
The flags argument used when the regex object was compiled, or 0 if no
|
||||
flags were provided.
|
||||
The flags argument used when the regex object was compiled, or
|
||||
\code{0} if no flags were provided.
|
||||
\end{datadesc}
|
||||
|
||||
\begin{datadesc}{groupindex}
|
||||
A dictionary mapping any symbolic group names (defined by
|
||||
\code{?P<\var{id}>}) to group numbers. The dictionary is empty if no
|
||||
A dictionary mapping any symbolic group names defined by
|
||||
\code{(?P<\var{id}>)} to group numbers. The dictionary is empty if no
|
||||
symbolic groups were used in the pattern.
|
||||
\end{datadesc}
|
||||
|
||||
|
|
@ -531,9 +527,7 @@ singleton tuple is returned in such cases.)
|
|||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{start}{\optional{group}}
|
||||
\end{funcdesc}
|
||||
|
||||
\begin{funcdesc}{end}{\optional{group}}
|
||||
\funcline{end}{\optional{group}}
|
||||
Return the indices of the start and end of the substring
|
||||
matched by \var{group}; \var{group} defaults to zero (meaning the whole
|
||||
matched substring).
|
||||
|
|
|
|||
Loading…
Reference in New Issue