summaryrefslogtreecommitdiffstats
path: root/Doc/lib/liblocale.tex
diff options
context:
space:
mode:
authorFred Drake <fdrake@acm.org>2000-10-25 20:59:52 (GMT)
committerFred Drake <fdrake@acm.org>2000-10-25 20:59:52 (GMT)
commit1491cace2a56fab274c5d26fd23539ceec3e1609 (patch)
tree18f5f0a048a9567b3fb4f64591efad778f8ae4c7 /Doc/lib/liblocale.tex
parent7cff7fe21fa6bcf541abc57900c28bfb351576d7 (diff)
downloadcpython-1491cace2a56fab274c5d26fd23539ceec3e1609.zip
cpython-1491cace2a56fab274c5d26fd23539ceec3e1609.tar.gz
cpython-1491cace2a56fab274c5d26fd23539ceec3e1609.tar.bz2
Several additions and updates based on text from Marc-Andre Lemburg
<mal@lemburg.com>. Lots of markup reformatting to make it easier for me to read & maintain.
Diffstat (limited to 'Doc/lib/liblocale.tex')
-rw-r--r--Doc/lib/liblocale.tex344
1 files changed, 221 insertions, 123 deletions
diff --git a/Doc/lib/liblocale.tex b/Doc/lib/liblocale.tex
index ee7665b..7f40f06 100644
--- a/Doc/lib/liblocale.tex
+++ b/Doc/lib/liblocale.tex
@@ -3,15 +3,15 @@
\declaremodule{standard}{locale}
\modulesynopsis{Internationalization services.}
-\moduleauthor{Martin von Loewis}{loewis@informatik.hu-berlin.de}
-\sectionauthor{Martin von Loewis}{loewis@informatik.hu-berlin.de}
+\moduleauthor{Martin von L\"owis}{loewis@informatik.hu-berlin.de}
+\sectionauthor{Martin von L\"owis}{loewis@informatik.hu-berlin.de}
-The \module{locale} module opens access to the \POSIX{} locale database
-and functionality. The \POSIX{} locale mechanism allows programmers
-to deal with certain cultural issues in an application, without
-requiring the programmer to know all the specifics of each country
-where the software is executed.
+The \module{locale} module opens access to the \POSIX{} locale
+database and functionality. The \POSIX{} locale mechanism allows
+programmers to deal with certain cultural issues in an application,
+without requiring the programmer to know all the specifics of each
+country where the software is executed.
The \module{locale} module is implemented on top of the
\module{_locale}\refbimodindex{_locale} module, which in turn uses an
@@ -21,170 +21,267 @@ The \module{locale} module defines the following exception and
functions:
-\begin{funcdesc}{setlocale}{category\optional{, value}}
-If \var{value} is specified, modifies the locale setting for the
-\var{category}. The available categories are listed in the data
-description below. The value is the name of a locale. An empty string
-specifies the user's default settings. If the modification of the
-locale fails, the exception \exception{Error} is
-raised. If successful, the new locale setting is returned.
+\begin{excdesc}{Error}
+ Exception raised when \function{setlocale()} fails.
+\end{excdesc}
+
+\begin{funcdesc}{setlocale}{category\optional{, locale}}
+ If \var{locale} is specified, it may be a string, a tuple of the
+ form \code{(\var{language code}, \var{encoding})}, or \code{None}.
+ If it is a tuple, it is converted to a string using the locale
+ aliasing engine. If \var{locale} is given and not \code{None},
+ \function{setlocale()} modifies the locale setting for the
+ \var{category}. The available categories are listed in the data
+ description below. The value is the name of a locale. An empty
+ string specifies the user's default settings. If the modification of
+ the locale fails, the exception \exception{Error} is raised. If
+ successful, the new locale setting is returned.
-If no \var{value} is specified, the current setting for the
-\var{category} is returned.
+ If \var{locale} is omitted or \code{None}, the current setting for
+ \var{category} is returned.
+
+ \function{setlocale()} is not thread safe on most systems.
+ Applications typically start with a call of
-\function{setlocale()} is not thread safe on most systems. Applications
-typically start with a call of
\begin{verbatim}
import locale
locale.setlocale(locale.LC_ALL,"")
\end{verbatim}
-This sets the locale for all categories to the user's default setting
-(typically specified in the \envvar{LANG} environment variable). If
-the locale is not changed thereafter, using multithreading should not
-cause problems.
-\end{funcdesc}
-\begin{excdesc}{Error}
-Exception raised when \function{setlocale()} fails.
-\end{excdesc}
+ This sets the locale for all categories to the user's default
+ setting (typically specified in the \envvar{LANG} environment
+ variable). If the locale is not changed thereafter, using
+ multithreading should not cause problems.
+
+ \versionchanged[Added support for tuple values of the \var{locale}
+ parameter]{2.0}
+\end{funcdesc}
\begin{funcdesc}{localeconv}{}
-Returns the database of of the local conventions as a dictionary. This
-dictionary has the following strings as keys:
-\begin{itemize}
-\item \code{decimal_point} specifies the decimal point used in
-floating point number representations for the \constant{LC_NUMERIC}
-category.
-\item \code{grouping} is a sequence of numbers specifying at which
-relative positions the \code{thousands_sep} is expected. If the
-sequence is terminated with \constant{CHAR_MAX}, no further
-grouping is performed. If the sequence terminates with a \code{0}, the last
-group size is repeatedly used.
-\item \code{thousands_sep} is the character used between groups.
-\item \code{int_curr_symbol} specifies the international currency
-symbol from the \constant{LC_MONETARY} category.
-\item \code{currency_symbol} is the local currency symbol.
-\item \code{mon_decimal_point} is the decimal point used in monetary
-values.
-\item \code{mon_thousands_sep} is the separator for grouping of
-monetary values.
-\item \code{mon_grouping} has the same format as the \code{grouping}
-key; it is used for monetary values.
-\item \code{positive_sign} and \code{negative_sign} gives the sign
-used for positive and negative monetary quantities.
-\item \code{int_frac_digits} and \code{frac_digits} specify the number
-of fractional digits used in the international and local formatting
-of monetary values.
-\item \code{p_cs_precedes} and \code{n_cs_precedes} specifies whether
-the currency symbol precedes the value for positive or negative
-values.
-\item \code{p_sep_by_space} and \code{n_sep_by_space} specifies
-whether there is a space between the positive or negative value and
-the currency symbol.
-\item \code{p_sign_posn} and \code{n_sign_posn} indicate how the
-sign should be placed for positive and negative monetary values.
-\end{itemize}
-
-The possible values for \code{p_sign_posn} and
-\code{n_sign_posn} are given below.
-
-\begin{tableii}{c|l}{code}{Value}{Explanation}
-\lineii{0}{Currency and value are surrounded by parentheses.}
-\lineii{1}{The sign should precede the value and currency symbol.}
-\lineii{2}{The sign should follow the value and currency symbol.}
-\lineii{3}{The sign should immediately precede the value.}
-\lineii{4}{The sign should immediately follow the value.}
-\lineii{LC_MAX}{Nothing is specified in this locale.}
-\end{tableii}
+ Returns the database of of the local conventions as a dictionary.
+ This dictionary has the following strings as keys:
+
+ \begin{itemize}
+ \item
+ \code{'decimal_point'} specifies the decimal point used in floating
+ point number representations for the \constant{LC_NUMERIC}
+ category.
+
+ \item
+ \code{'groupin'} is a sequence of numbers specifying at which
+ relative positions the \code{'thousands_sep'} is expected. If the
+ sequence is terminated with \constant{CHAR_MAX}, no further
+ grouping is performed. If the sequence terminates with a \code{0},
+ the last group size is repeatedly used.
+
+ \item
+ \code{'thousands_sep'} is the character used between groups.
+
+ \item
+ \code{'int_curr_symbol'} specifies the international currency
+ symbol from the \constant{LC_MONETARY} category.
+
+ \item
+ \code{'currency_symbol'} is the local currency symbol.
+
+ \item
+ \code{'mon_decimal_point'} is the decimal point used in monetary
+ values.
+
+ \item
+ \code{'mon_thousands_sep'} is the separator for grouping of
+ monetary values.
+
+ \item
+ \code{'mon_grouping'} has the same format as the \code{'grouping'}
+ key; it is used for monetary values.
+
+ \item
+ \code{'positive_sign'} and \code{'negative_sign'} gives the sign
+ used for positive and negative monetary quantities.
+
+ \item
+ \code{'int_frac_digits'} and \code{'frac_digits'} specify the number
+ of fractional digits used in the international and local
+ formatting of monetary values.
+
+ \item
+ \code{'p_cs_precedes'} and \code{'n_cs_precedes'} specifies whether
+ the currency symbol precedes the value for positive or negative
+ values.
+
+ \item
+ \code{'p_sep_by_space'} and \code{'n_sep_by_space'} specifies
+ whether there is a space between the positive or negative value
+ and the currency symbol.
+
+ \item
+ \code{'p_sign_posn'} and \code{'n_sign_posn'} indicate how the
+ sign should be placed for positive and negative monetary values.
+ \end{itemize}
+
+ The possible values for \code{p_sign_posn} and
+ \code{n_sign_posn} are given below.
+
+ \begin{tableii}{c|l}{code}{Value}{Explanation}
+ \lineii{0}{Currency and value are surrounded by parentheses.}
+ \lineii{1}{The sign should precede the value and currency symbol.}
+ \lineii{2}{The sign should follow the value and currency symbol.}
+ \lineii{3}{The sign should immediately precede the value.}
+ \lineii{4}{The sign should immediately follow the value.}
+ \lineii{LC_MAX}{Nothing is specified in this locale.}
+ \end{tableii}
\end{funcdesc}
-\begin{funcdesc}{strcoll}{string1,string2}
-Compares two strings according to the current \constant{LC_COLLATE}
-setting. As any other compare function, returns a negative, or a
-positive value, or \code{0}, depending on whether \var{string1}
-collates before or after \var{string2} or is equal to it.
+\begin{funcdesc}{getdefaultlocale}{\optional{envvars}}
+ Tries to determine the default locale settings and returns
+ them as a tuple of the form \code{(\var{language code},
+ \var{encoding})}.
+
+ According to \POSIX, a program which has not called
+ \code{setlocale(LC_ALL, '')} runs using the portable \code{'C'}
+ locale. Calling \code{setlocale(LC_ALL, '')} lets it use the
+ default locale as defined by the \envvar{LANG} variable. Since we
+ do not want to interfere with the current locale setting we thus
+ emulate the behavior in the way described above.
+
+ To maintain compatibility with other platforms, not only the
+ \envvar{LANG} variable is tested, but a list of variables given as
+ envvars parameter. The first found to be defined will be
+ used. \var{envvars} defaults to the search path used in GNU gettext;
+ it must always contain the variable name \samp{LANG}. The GNU
+ gettext search path contains \code{'LANGUAGE'}, \code{'LC_ALL'},
+ code{'LC_CTYPE'}, and \code{'LANG'}, in that order.
+
+ Except for the code \code{'C'}, the language code corresponds to
+ \rfc{1766}. \var{language code} and \var{encoding} may be
+ \code{None} if their values cannot be determined.
+ \versionadded{2.0}
+\end{funcdesc}
+
+\begin{funcdesc}{getlocale}{\optional{category}}
+ Returns the current setting for the given locale category as
+ tuple (language code, encoding). \var{category} may be one of the
+ \constant{LC_*} values except \constant{LC_ALL}. It defaults to
+ \constant{LC_CTYPE}.
+
+ Except for the code \code{'C'}, the language code corresponds to
+ \rfc{1766}. \var{language code} and \var{encoding} may be
+ \code{None} if their values cannot be determined.
+ \versionadded{2.0}
+\end{funcdesc}
+
+\begin{funcdesc}{normalize}{localename}
+ Returns a normalized locale code for the given locale name. The
+ returned locale code is formatted for use with
+ \function{setlocale()}. If normalization fails, the original name
+ is returned unchanged.
+
+ If the given encoding is not known, the function defaults to
+ the default encoding for the locale code just like
+ \function{setlocale()}.
+ \versionadded{2.0}
+\end{funcdesc}
+
+\begin{funcdesc}{resetlocale}{\optional{category}}
+ Sets the locale for \var{category} to the default setting.
+
+ The default setting is determined by calling
+ \function{getdefaultlocale()}. \var{category} defaults to
+ \constant{LC_ALL}.
+ \versionadded{2.0}
+\end{funcdesc}
+
+\begin{funcdesc}{strcoll}{string1, string2}
+ Compares two strings according to the current
+ \constant{LC_COLLATE} setting. As any other compare function,
+ returns a negative, or a positive value, or \code{0}, depending on
+ whether \var{string1} collates before or after \var{string2} or is
+ equal to it.
\end{funcdesc}
\begin{funcdesc}{strxfrm}{string}
-Transforms a string to one that can be used for the built-in function
-\function{cmp()}\bifuncindex{cmp}, and still returns locale-aware
-results. This function can be used when the same string is compared
-repeatedly, e.g. when collating a sequence of strings.
+ Transforms a string to one that can be used for the built-in
+ function \function{cmp()}\bifuncindex{cmp}, and still returns
+ locale-aware results. This function can be used when the same
+ string is compared repeatedly, e.g. when collating a sequence of
+ strings.
\end{funcdesc}
-\begin{funcdesc}{format}{format, val, \optional{grouping\code{ = 0}}}
-Formats a number \var{val} according to the current
-\constant{LC_NUMERIC} setting. The format follows the conventions of
-the \code{\%} operator. For floating point values, the decimal point
-is modified if appropriate. If \var{grouping} is true, also takes the
-grouping into account.
+\begin{funcdesc}{format}{format, val\optional{, grouping}}
+ Formats a number \var{val} according to the current
+ \constant{LC_NUMERIC} setting. The format follows the conventions
+ of the \code{\%} operator. For floating point values, the decimal
+ point is modified if appropriate. If \var{grouping} is true, also
+ takes the grouping into account.
\end{funcdesc}
\begin{funcdesc}{str}{float}
-Formats a floating point number using the same format as the built-in
-function \code{str(\var{float})}, but takes the decimal point into
-account.
+ Formats a floating point number using the same format as the
+ built-in function \code{str(\var{float})}, but takes the decimal
+ point into account.
\end{funcdesc}
\begin{funcdesc}{atof}{string}
-Converts a string to a floating point number, following the
-\constant{LC_NUMERIC} settings.
+ Converts a string to a floating point number, following the
+ \constant{LC_NUMERIC} settings.
\end{funcdesc}
\begin{funcdesc}{atoi}{string}
-Converts a string to an integer, following the \constant{LC_NUMERIC}
-conventions.
+ Converts a string to an integer, following the
+ \constant{LC_NUMERIC} conventions.
\end{funcdesc}
\begin{datadesc}{LC_CTYPE}
\refstmodindex{string}
-Locale category for the character type functions. Depending on the
-settings of this category, the functions of module \refmodule{string}
-dealing with case change their behaviour.
+ Locale category for the character type functions. Depending on the
+ settings of this category, the functions of module
+ \refmodule{string} dealing with case change their behaviour.
\end{datadesc}
\begin{datadesc}{LC_COLLATE}
-Locale category for sorting strings. The functions
-\function{strcoll()} and \function{strxfrm()} of the \module{locale}
-module are affected.
+ Locale category for sorting strings. The functions
+ \function{strcoll()} and \function{strxfrm()} of the
+ \module{locale} module are affected.
\end{datadesc}
\begin{datadesc}{LC_TIME}
-Locale category for the formatting of time. The function
-\function{time.strftime()} follows these conventions.
+ Locale category for the formatting of time. The function
+ \function{time.strftime()} follows these conventions.
\end{datadesc}
\begin{datadesc}{LC_MONETARY}
-Locale category for formatting of monetary values. The available
-options are available from the \function{localeconv()} function.
+ Locale category for formatting of monetary values. The available
+ options are available from the \function{localeconv()} function.
\end{datadesc}
\begin{datadesc}{LC_MESSAGES}
-Locale category for message display. Python currently does not support
-application specific locale-aware messages. Messages displayed by the
-operating system, like those returned by \function{os.strerror()}
-might be affected by this category.
+ Locale category for message display. Python currently does not
+ support application specific locale-aware messages. Messages
+ displayed by the operating system, like those returned by
+ \function{os.strerror()} might be affected by this category.
\end{datadesc}
\begin{datadesc}{LC_NUMERIC}
-Locale category for formatting numbers. The functions
-\function{format()}, \function{atoi()}, \function{atof()} and
-\function{str()} of the \module{locale} module are affected by that
-category. All other numeric formatting operations are not affected.
+ Locale category for formatting numbers. The functions
+ \function{format()}, \function{atoi()}, \function{atof()} and
+ \function{str()} of the \module{locale} module are affected by that
+ category. All other numeric formatting operations are not
+ affected.
\end{datadesc}
\begin{datadesc}{LC_ALL}
-Combination of all locale settings. If this flag is used when the
-locale is changed, setting the locale for all categories is
-attempted. If that fails for any category, no category is changed at
-all. When the locale is retrieved using this flag, a string indicating
-the setting for all categories is returned. This string can be later
-used to restore the settings.
+ Combination of all locale settings. If this flag is used when the
+ locale is changed, setting the locale for all categories is
+ attempted. If that fails for any category, no category is changed at
+ all. When the locale is retrieved using this flag, a string
+ indicating the setting for all categories is returned. This string
+ can be later used to restore the settings.
\end{datadesc}
\begin{datadesc}{CHAR_MAX}
-This is a symbolic constant used for different values returned by
-\function{localeconv()}.
+ This is a symbolic constant used for different values returned by
+ \function{localeconv()}.
\end{datadesc}
Example:
@@ -199,6 +296,7 @@ Example:
>>> locale.setlocale(locale.LC_ALL, loc) # restore saved locale
\end{verbatim}
+
\subsection{Background, details, hints, tips and caveats}
The C standard defines the locale as a program-wide property that may
@@ -243,8 +341,8 @@ is to use the special functions defined by this module:
\function{atof()}, \function{atoi()}, \function{format()},
\function{str()}.
-\subsection{For extension writers and programs that embed Python}
-\label{embedding-locale}
+\subsection{For extension writers and programs that embed Python
+ \label{embedding-locale}}
Extension modules should never call \function{setlocale()}, except to
find out what the current locale is. But since the return value can