[Python-checkins] python/dist/src/Doc/lib libcsv.tex,1.18,1.19

[montanaro at users.sourceforge.net]

Update of /cvsroot/python/python/dist/src/Doc/lib
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv22325

Modified Files:
	libcsv.tex 
Log Message:
add UnicodeReader and UnicodeWriter example classes



Index: libcsv.tex
===================================================================
RCS file: /cvsroot/python/python/dist/src/Doc/lib/libcsv.tex,v
retrieving revision 1.18
retrieving revision 1.19
diff -u -d -r1.18 -r1.19
--- libcsv.tex	12 Jan 2005 11:47:57 -0000	1.18
+++ libcsv.tex	18 Mar 2005 16:56:37 -0000	1.19
@@ -424,3 +424,38 @@
 print csv.reader(['one,two,three'])[0]
 \end{verbatim}
 
+The \module{csv} module doesn't directly support reading and writing
+Unicode, but it is 8-bit clean save for some problems with \ASCII{} NUL
+characters, so you can write classes that handle the encoding and decoding
+for you as long as you avoid encodings like utf-16 that use NULs.
+
+\begin{verbatim}
+import csv
+
+class UnicodeReader:
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        self.reader = csv.reader(f, dialect=dialect, **kwds)
+        self.encoding = encoding
+
+    def next(self):
+        row = self.reader.next()
+        return [unicode(s, self.encoding) for s in row]
+
+    def __iter__(self):
+        return self
+
+class UnicodeWriter:
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        self.writer = csv.writer(f, dialect=dialect, **kwds)
+        self.encoding = encoding
+
+    def writerow(self, row):
+        self.writer.writerow([s.encode("utf-8") for s in row])
+
+    def writerows(self, rows):
+        for row in rows:
+            self.writerow(row)
+\end{verbatim}
+
+They should work just like the \class{csv.reader} and \class{csv.writer}
+classes but add an \var{encoding} parameter.