summaryrefslogtreecommitdiffstats
path: root/Doc
diff options
context:
space:
mode:
authorFred Drake <fdrake@acm.org>2000-06-13 20:50:50 (GMT)
committerFred Drake <fdrake@acm.org>2000-06-13 20:50:50 (GMT)
commit28b294459d04682a6aefc0e2db34dfa1d454e6b8 (patch)
tree000a0725839ea8f039d8be02275e1b851198272d /Doc
parent414ca6666ccbf5ac2caac0f60c07b686d03cda49 (diff)
downloadcpython-28b294459d04682a6aefc0e2db34dfa1d454e6b8.zip
cpython-28b294459d04682a6aefc0e2db34dfa1d454e6b8.tar.gz
cpython-28b294459d04682a6aefc0e2db34dfa1d454e6b8.tar.bz2
Marc-Andre Lemburg <mal@lemburg.com>:
Documentation for the unicodedata module (massaged by Fred for minor consistency issues).
Diffstat (limited to 'Doc')
-rw-r--r--Doc/lib/libunicodedata.tex72
1 files changed, 72 insertions, 0 deletions
diff --git a/Doc/lib/libunicodedata.tex b/Doc/lib/libunicodedata.tex
new file mode 100644
index 0000000..1eae492
--- /dev/null
+++ b/Doc/lib/libunicodedata.tex
@@ -0,0 +1,72 @@
+\section{\module{unicodedata} ---
+ Unicode Database}
+
+\declaremodule{standard}{unicodedata}
+\modulesynopsis{Access the Unicode Database.}
+\moduleauthor{Marc-Andre Lemburg}{mal@lemburg.com}
+\sectionauthor{Marc-Andre Lemburg}{mal@lemburg.com}
+
+
+\index{Unicode}
+\index{character}
+\indexii{Unicode}{database}
+
+This module provides access to the Unicode Character Database which
+defines character properties for all Unicode characters. The data in
+this database is based on the \file{UnicodeData.txt} file version
+3.0.0 which is publically available from \url{ftp://ftp.unicode.org/}.
+
+The module uses the same names and symbols as defined by the
+UnicodeData File Format 3.0.0 (see
+\url{ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.html}). It
+defines the following functions:
+
+\begin{funcdesc}{decimal}{unichr\optional{, default}}
+ Returns the decimal value assigned to the Unicode character
+ \var{unichr} as integer. If no such value is defined,
+ \var{default} is returned, or, if not given,
+ \exception{ValueError} is raised.
+\end{funcdesc}
+
+\begin{funcdesc}{digit}{unichr\optional{, default}}
+ Returns the digit value assigned to the Unicode character
+ \var{unichr} as integer. If no such value is defined,
+ \var{default} is returned, or, if not given,
+ \exception{ValueError} is raised.
+\end{funcdesc}
+
+\begin{funcdesc}{numeric}{unichr\optional{, default}}
+ Returns the numeric value assigned to the Unicode character
+ \var{unichr} as float. If no such value is defined, \var{default} is
+ returned, or, if not given, \exception{ValueError} is raised.
+\end{funcdesc}
+
+\begin{funcdesc}{category}{unichr}
+ Returns the general category assigned to the Unicode character
+ \var{unichr} as string.
+\end{funcdesc}
+
+\begin{funcdesc}{bidirectional}{unichr}
+ Returns the bidirectional category assigned to the Unicode character
+ \var{unichr} as string. If no such value is defined, an empty string
+ is returned.
+\end{funcdesc}
+
+\begin{funcdesc}{combining}{unichr}
+ Returns the canonical combining class assigned to the Unicode
+ character \var{unichr} as integer. Returns \code{0} if no combining
+ class is defined.
+\end{funcdesc}
+
+\begin{funcdesc}{mirrored}{unichr}
+ Returns the mirrored property of assigned to the Unicode character
+ \var{unichr} as integer. Returns \code{1} if the character has been
+ identified as a ``mirrored'' character in bidirectional text,
+ \code{0} otherwise.
+\end{funcdesc}
+
+\begin{funcdesc}{decomposition}{unichr}
+ Returns the character decomposition mapping assigned to the Unicode
+ character \var{unichr} as string. An empty string is returned in case
+ no such mapping is defined.
+\end{funcdesc}