Removed dependency on xml.sax.saxutils.escape, and implemented it inline as _xml_escape.

Fixed typo in ParseResults.insert, referencing invalid var 'j' (replaced with 'index')
Fixed error in replaceHTMLEntity, mapping " to ', now correctly maps to "

git-svn-id: svn://svn.code.sf.net/p/pyparsing/code/src@158 9bf210a0-9d2d-494c-87cf-cfb32e7dff7b

2 files changed, 33 insertions, 8 deletions

diff --git a/CHANGES b/CHANGES
index 8bf458f..8ccd35d 100644
--- a/CHANGES
+++ b/CHANGES
@@ -2,6 +2,22 @@
 Change Log

 ==========

 

+Version 1.5.1 - ???, 2008

+--------------------------

+- Added optional parseAll argument to parseFile, to be consistent

+  with parseAll argument to parseString.  Posted by pboucher on the

+  pyparsing wiki, thanks!

+

+- Removed dependency on xml.sax.saxutils.escape, and included

+  internal implementation instead - proposed by Mike Droettboom on

+  the pyparsing mailing list, thanks Mike!  Also fixed erroneous 

+  mapping in replaceHTMLEntity of &quot to ', now correctly maps 

+  to ".

+

+- Fixed typo in ParseResults.insert, found by Alejandro Dubrovsky,

+  good catch!

+  

+

 Version 1.5.0 - June, 2008

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

 This version of pyparsing includes work on two long-standing

diff --git a/pyparsing.py b/pyparsing.py
index e232834..e9a87e7 100644
--- a/pyparsing.py
+++ b/pyparsing.py
@@ -68,7 +68,6 @@ import copy,sys
 import warnings

 import re

 import sre_constants

-import xml.sax.saxutils

 #~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )

 

 __all__ = [

@@ -135,6 +134,16 @@ def _str2dict(strg):
     return dict( [(c,0) for c in strg] )

     #~ return set( [c for c in strg] )

 

+def _xml_escape(data):

+    """Escape &, <, >, ', etc. in a string of data."""

+

+    # ampersand must be replaced first

+    from_symbols = '&><"'

+    to_symbols = ['&'+s+';' for s in "amp gt lt quot".split()]

+    for from_,to_ in zip(from_symbols, to_symbols):

+        data = data.replace(from_, to_)

+    return data

+

 class _Constants(object):

     pass

 

@@ -375,7 +384,7 @@ class ParseResults(object):
         for name in self.__tokdict:

             occurrences = self.__tokdict[name]

             for k, (value, position) in enumerate(occurrences):

-                occurrences[k] = _ParseResultsWithOffset(value, position + (position > j))

+                occurrences[k] = _ParseResultsWithOffset(value, position + (position > index))

 

     def items( self ):

         """Returns all named result keys and values as a list of tuples."""

@@ -518,7 +527,7 @@ class ParseResults(object):
                         continue

                     else:

                         resTag = "ITEM"

-                xmlBodyText = xml.sax.saxutils.escape(_ustr(res))

+                xmlBodyText = _xml_escape(_ustr(res))

                 out += [ nl, nextLevelIndent, "<", resTag, ">",

                                                 xmlBodyText,

                                                 "</", resTag, ">" ]

@@ -3481,16 +3490,16 @@ def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString):
     return ret

 

 def indentedBlock(blockStatementExpr, indentStack, indent=True):

-    """Helper method for defining space-delimited indentation blocks, such as 

+    """Helper method for defining space-delimited indentation blocks, such as

        those used to define block statements in Python source code.

-       

+

        Parameters:

-        - blockStatementExpr - expression defining syntax of statement that 

+        - blockStatementExpr - expression defining syntax of statement that

             is repeated within the indented block

         - indentStack - list created by caller to manage indentation stack

             (multiple statementWithIndentedBlock expressions within a single grammar

             should share a common indentStack)

-        - indent - boolean indicating whether block must be indented beyond the 

+        - indent - boolean indicating whether block must be indented beyond the

             the current level; set to False for block of left-most statements

             (default=True)

 

@@ -3537,7 +3546,7 @@ punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]")
 

 anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:"))

 commonHTMLEntity = Combine(_L("&") + oneOf("gt lt amp nbsp quot").setResultsName("entity") +";")

-_htmlEntityMap = dict(zip("gt lt amp nbsp quot".split(),"><& '"))

+_htmlEntityMap = dict(zip("gt lt amp nbsp quot".split(),'><& "'))

 replaceHTMLEntity = lambda t : t.entity in _htmlEntityMap and _htmlEntityMap[t.entity] or None

 

 # it's easy to get these comment structures wrong - they're very common, so may as well make them available