Added default behavior to QuotedString to convert embedded '\t', '\n', etc. characters to their whitespace counterparts; added support in new init arg, convertWhitespaceEscapes.

git-svn-id: svn://svn.code.sf.net/p/pyparsing/code/trunk@330 9bf210a0-9d2d-494c-87cf-cfb32e7dff7b

3 files changed, 36 insertions, 2 deletions

diff --git a/src/CHANGES b/src/CHANGES
index f615f4d..2a2bd57 100644
--- a/src/CHANGES
+++ b/src/CHANGES
@@ -19,6 +19,10 @@ Version 2.1.1 -
   an ambiguous signature for the generated parse action, which fails in 

   PyPy. Reported by Evan Hubinger, thanks Evan!

 

+- Added default behavior to QuotedString to convert embedded '\t', '\n',

+  etc. characters to their whitespace counterparts. Found during Q&A

+  exchange on SO with Maxim.

+

 

 Version 2.1.0 - February, 2016

 ------------------------------

diff --git a/src/pyparsing.py b/src/pyparsing.py
index b1d5598..0e62423 100644
--- a/src/pyparsing.py
+++ b/src/pyparsing.py
@@ -58,7 +58,7 @@ The pyparsing module handles some of the problems that are typically vexing when
 """

 

 __version__ = "2.1.1"

-__versionTime__ = "5 Mar 2016 23:42"

+__versionTime__ = "19 Mar 2016 22:48 UTC"

 __author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"

 

 import string

@@ -1941,7 +1941,7 @@ class Regex(Token):
 class QuotedString(Token):

     """Token for matching strings that are delimited by quoting characters.

     """

-    def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None):

+    def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None, convertWhitespaceEscapes=True):

         """

            Defined with the following parameters:

             - quoteChar - string of one or more characters defining the quote delimiting string

@@ -1950,6 +1950,7 @@ class QuotedString(Token):
             - multiline - boolean indicating whether quotes can span multiple lines (default=C{False})

             - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True})

             - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar)

+            - convertWhitespaceEscapes - convert escaped whitespace ('\t', '\n', etc.) to actual whitespace (default=C{True})

         """

         super(QuotedString,self).__init__()

 

@@ -1975,6 +1976,7 @@ class QuotedString(Token):
         self.escChar = escChar

         self.escQuote = escQuote

         self.unquoteResults = unquoteResults

+        self.convertWhitespaceEscapes = convertWhitespaceEscapes

 

         if multiline:

             self.flags = re.MULTILINE | re.DOTALL

@@ -2028,6 +2030,17 @@ class QuotedString(Token):
             ret = ret[self.quoteCharLen:-self.endQuoteCharLen]

 

             if isinstance(ret,basestring):

+                # replace escaped whitespace

+                if '\\' in ret and self.convertWhitespaceEscapes:

+                    ws_map = {

+                        r'\t' : '\t',

+                        r'\n' : '\n',

+                        r'\f' : '\f',

+                        r'\r' : '\r',

+                    }

+                    for wslit,wschar in ws_map.items():

+                        ret = ret.replace(wslit, wschar)

+

                 # replace escaped characters

                 if self.escChar:

                     ret = re.sub(self.escCharReplacePattern,"\g<1>",ret)

diff --git a/src/update_pyparsing_timestamp.py b/src/update_pyparsing_timestamp.py
new file mode 100644
index 0000000..80ea3d4
--- /dev/null
+++ b/src/update_pyparsing_timestamp.py
@@ -0,0 +1,17 @@
+from pyparsing import quotedString

+from datetime import datetime

+

+nw = datetime.utcnow()

+nowstring = '"%s"' % (nw.strftime("%d %b %Y %X")[:-3] + " UTC")

+print (nowstring)

+

+quoted_time = quotedString()

+quoted_time.setParseAction(lambda: nowstring)

+

+version_time = "__versionTime__ = " + quoted_time

+with open('pyparsing.py') as oldpp:

+    new_code = version_time.transformString(oldpp.read())

+

+with open('pyparsing.py','w') as newpp:

+    newpp.write(new_code)

+