Make the fieldnames argument optional in the DictReader. If self.fieldnames

is None, the next row read is used as the fieldnames.  In the common case,
this means the programmer doesn't need to know the fieldnames ahead of time.
The first row of the file will be used.  In the uncommon case, this means
the programmer can set the reader's fieldnames attribute to None at any time
and have the next row read as the next set of fieldnames, so a csv file can
contain several "sections", each with different fieldnames.

diff --git a/Doc/lib/libcsv.tex b/Doc/lib/libcsv.tex
index e2877ee6ad72651bf4a4569dbfad3a8270e7c6ba..bf8b0bf789c34307e1cffcdaac76e0252b8bbef4 100644 (file)
--- a/Doc/lib/libcsv.tex
+++ b/Doc/lib/libcsv.tex
@@ -117,14 +117,18 @@ Return the names of all registered dialects.
 
 The \module{csv} module defines the following classes:
 
-\begin{classdesc}{DictReader}{csvfile, fieldnames\optional{,
+\begin{classdesc}{DictReader}{csvfile\optional{,
+                             fieldnames=\constant{None},\optional{,
                               restkey=\constant{None}\optional{,
                              restval=\constant{None}\optional{,
                               dialect=\code{'excel'}\optional{,
-                             fmtparam}}}}}
+                             fmtparam}}}}}}
 Create an object which operates like a regular reader but maps the
-information read into a dict whose keys are given by the \var{fieldnames}
-parameter.  If the row read has fewer fields than the fieldnames sequence,
+information read into a dict whose keys are given by the optional
+{} \var{fieldnames}
+parameter.  If the \var{fieldnames} parameter is omitted, the values in
+the first row of the \var{csvfile} will be used as the fieldnames.
+If the row read has fewer fields than the fieldnames sequence,
 the value of \var{restval} will be used as the default value.  If the row
 read has more fields than the fieldnames sequence, the remaining data is
 added as a sequence keyed by the value of \var{restkey}.  If the row read
@@ -149,6 +153,13 @@ method contains a key not found in \var{fieldnames}, the optional
 to \code{'raise'} a \exception{ValueError} is raised.  If it is set to
 \code{'ignore'}, extra values in the dictionary are ignored.  All other
 parameters are interpreted as for \class{writer} objects.
+
+Note that unlike the \class{DictReader} class, the \var{fieldnames}
+parameter of the \class{DictWriter} is not optional.  Since Python's
+\class{dict} objects are not ordered, there is not enough information
+available to deduce the order in which the row should be written to the
+\var{csvfile}.
+
 \end{classdesc}
 
 \begin{classdesc*}{Dialect}{}

diff --git a/Lib/csv.py b/Lib/csv.py
index 096badc7bbc25923c241dc3636056ca34632f2ee..f2389fd30425944a39163b92ae7b36f118efe300 100644 (file)
--- a/Lib/csv.py
+++ b/Lib/csv.py
@@ -92,7 +92,7 @@ register_dialect("excel-tab", excel_tab)
 
 
 class DictReader:
-    def __init__(self, f, fieldnames, restkey=None, restval=None,
+    def __init__(self, f, fieldnames=None, restkey=None, restval=None,
                  dialect="excel", *args, **kwds):
         self.fieldnames = fieldnames    # list of keys for the dict
         self.restkey = restkey          # key to catch long rows
@@ -104,6 +104,10 @@ class DictReader:
 
     def next(self):
         row = self.reader.next()
+        if self.fieldnames is None:
+            self.fieldnames = row
+            row = self.reader.next()
+
         # unlike the basic reader, we prefer not to return blanks,
         # because we will typically wind up with a dict full of None
         # values

diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py
index d85c5b6cb39d487b0da333236f409cd26b9f025c..29a13cb7a0ec7a1b8d94f774c143a217d6a380a7 100644 (file)
--- a/Lib/test/test_csv.py
+++ b/Lib/test/test_csv.py
@@ -382,7 +382,6 @@ class TestQuotedEscapedExcel(TestCsvBase):
     def test_read_escape_fieldsep(self):
         self.readerAssertEqual('"abc\\,def"\r\n', [['abc,def']])
 
-# Disabled, pending support in csv.utils module
 class TestDictFields(unittest.TestCase):
     ### "long" means the row is longer than the number of fieldnames
     ### "short" means there are fewer elements in the row than fieldnames
@@ -401,6 +400,10 @@ class TestDictFields(unittest.TestCase):
                                 fieldnames=["f1", "f2", "f3"])
         self.assertEqual(reader.next(), {"f1": '1', "f2": '2', "f3": 'abc'})
 
+    def test_read_dict_no_fieldnames(self):
+        reader = csv.DictReader(StringIO("f1,f2,f3\r\n1,2,abc\r\n"))
+        self.assertEqual(reader.next(), {"f1": '1', "f2": '2', "f3": 'abc'})
+
     def test_read_long(self):
         reader = csv.DictReader(StringIO("1,2,abc,4,5,6\r\n"),
                                 fieldnames=["f1", "f2"])
@@ -413,6 +416,12 @@ class TestDictFields(unittest.TestCase):
         self.assertEqual(reader.next(), {"f1": '1', "f2": '2',
                                          "_rest": ["abc", "4", "5", "6"]})
 
+    def test_read_long_with_rest_no_fieldnames(self):
+        reader = csv.DictReader(StringIO("f1,f2\r\n1,2,abc,4,5,6\r\n"),
+                                restkey="_rest")
+        self.assertEqual(reader.next(), {"f1": '1', "f2": '2',
+                                         "_rest": ["abc", "4", "5", "6"]})
+
     def test_read_short(self):
         reader = csv.DictReader(["1,2,abc,4,5,6\r\n","1,2,abc\r\n"],
                                 fieldnames="1 2 3 4 5 6".split(),