[gnue] r7874 - in trunk/gnue-common: src/utils tests

[jamest]

Author: jamest
Date: 2005-08-23 14:32:54 -0500 (Tue, 23 Aug 2005)
New Revision: 7874

Modified:
   trunk/gnue-common/src/utils/TextUtils.py
   trunk/gnue-common/tests/utils_TextUtils.py
Log:
added stripHTML function to TextUtils
more unit tests for TextUtils
misc cleanup


Modified: trunk/gnue-common/src/utils/TextUtils.py
===================================================================
--- trunk/gnue-common/src/utils/TextUtils.py    2005-08-22 14:31:33 UTC (rev 
7873)
+++ trunk/gnue-common/src/utils/TextUtils.py    2005-08-23 19:32:54 UTC (rev 
7874)
@@ -21,20 +21,21 @@
 # FILE:
 # TextUtils.py
 #
-# DESCRIPTION:
-# Common text-related utilities
-#
 # NOTES:
-#
+"""
+Common text-related utilities
+"""
+__revision__ = "$Id"
 
-import string
+import formatter, htmllib, StringIO
 
-ALIGN_LEFT=0
-ALIGN_RIGHT=1
-ALIGN_CENTER=2
+ALIGN_LEFT   = 0
+ALIGN_RIGHT  = 1
+ALIGN_CENTER = 2
 
 # very simple lineWrap
-def lineWrap(message,maxWidth, preserveNewlines=1, alignment=ALIGN_LEFT, 
eol=1):
+def lineWrap(message, maxWidth, preserveNewlines=1, 
+             alignment=ALIGN_LEFT, eol=1):
   """
   A simple linewrap function.
 
@@ -56,21 +57,21 @@
 
   text = ""
 
-  temptext = string.strip(str(message))
+  temptext = str(message).strip()
   if preserveNewlines:
-    buff = string.split(temptext,"\n")
+    buff = temptext.split("\n")
   else:
-    buff = (temptext,)
+    buff = (temptext, )
 
   for strings in buff:
     while len(strings) > maxWidth:
       index = 0
 
-      for sep in [' ',',',':','.',';']:
-        ind = string.rfind(strings,sep,0,maxWidth-1)+1
-        if ind > index: index = ind
+      for sep in [' ', ',', ':', '.', ';']:
+        ind = strings.rfind(sep, 0, maxWidth-1)+1
+        index = max(ind, index)
 
-      if index > maxWidth or index==0:
+      if index > maxWidth or index == 0:
         index = maxWidth-1
 
       line = strings[:index]
@@ -117,7 +118,7 @@
   @return: The converted value
   @rtype: number
   """
-  if text[-1] in ('0','1','2','3','4','5','6','7','8','9'):
+  if text[-1].isdigit():
     value = float(text) / 72 * multiplier
   else:
     unit = text[-2:]
@@ -143,18 +144,18 @@
   @return: The roman numeral equivalent.
   @rtype: string
   """
-  n = int(num) # just in case
-  rv = ""
-  for dec, rom in (
+  number = int(num) # just in case
+  output = ""
+  for dec, roman in (
       (1000, 'M'), (900, 'CM', ),
       (500, 'D'), (400, 'CD'), (100, 'C'),
       (90, 'XC'),(50, 'L'), (40, 'XL'),
       (10, 'X'), (9, 'IX'), (5, 'V'),
       (4, 'IV'), (1, 'I') ):
-    while (n >= dec):
-      n -= dec;
-      rv += rom;
-  return rv
+    while (number >= dec):
+      number -= dec;
+      output += roman;
+  return output
 
 
 def dollarToText(num):
@@ -175,24 +176,25 @@
   """
   whole = int(num)
   cents = round((num-whole)*100)
-  rv = 'and %02d/100' % cents
+  output = 'and %02d/100' % cents
   if whole:
     thirdRange = 0
     while whole:
       whole, segment = divmod(whole, 1000)
       hundreds, tens = divmod(segment, 100)
       try:
-        rv = _smallDollarMap[tens] + _thirdDollarMap[thirdRange] + rv
+        output = _smallDollarMap[tens] + _thirdDollarMap[thirdRange] + output
       except IndexError:
-        ten, ones = divmod(tens,10)
-        rv = _tenDollarMap[ten] + _smallDollarMap[ones] + 
_thirdDollarMap[thirdRange] + rv
+        ten, ones = divmod(tens, 10)
+        output = _tenDollarMap[ten] + _smallDollarMap[ones] + \
+                 _thirdDollarMap[thirdRange] + output
       if hundreds:
-        rv = _smallDollarMap[hundreds] + 'Hundred ' + rv
+        output = _smallDollarMap[hundreds] + 'Hundred ' + output
       thirdRange += 1
   else:
-    rv = 'Zero ' + rv
+    output = 'Zero ' + output
 
-  return rv
+  return output
 
 
 _smallDollarMap = ('', 'One ', 'Two ', 'Three ', 'Four ', 'Five ',
@@ -207,7 +209,7 @@
 
 
 # Comify a number
-def comify(num, decimals=2, parenthesis=0):
+def comify(num, decimals=2, parenthesis=False):
   """
   Comify a number (e.g., print -9900 as -9,900.00)
 
@@ -223,34 +225,81 @@
   @param decimals: The number of decimal places to retain
   @type decimals: number
   @param parenthesis: If true then negative numbers will be returned inside 
parenthesis
-  @type  parenthesis: number
+  @type  parenthesis: boolean
 
   @return: A properly formatted number
   @rtype: string
   """
   neg = num < 0
   num = abs(num)
-  whole, dec = (string.split(string.strip(("%%12.%sf" % decimals) % 
abs(num)),'.') + [""])[:2]
+  whole, dec = ( ( ( ("%%12.%sf" % decimals) % abs(num)).strip()).split('.') +
+                 [""])[:2]
   if len(dec):
     dec = "." + dec
 
-  s = ""
+  output = ""
 
-  for i in range(divmod(len(whole),3)[0]+1):
+  for i in range(divmod(len(whole), 3)[0]+1):
     j = len(whole) - i*3
-    s = "," + whole[j > 3 and j-3 or 0:j] + s
+    output = "," + whole[j > 3 and j-3 or 0:j] + output
 
-  s += dec
+  output += dec
 
-  while s[:1] == ',':
-    s = s[1:]
+  while output[:1] == ',':
+    output = output[1:]
 
   if neg:
     if parenthesis:
-      s = "(%s)" % s
+      output = "(%s)" % output
     else:
-      s = "-" + s
+      output = "-" + output
   elif parenthesis:
-    s += " "
+    output += " "
 
-  return s
+  return output
+
+  
+def stripHTML(htmlString):
+  """
+  Removes all html mark-up from a text string.
+  
+  @param htmlString: The text containing the html mark up
+  @type htmlString: String
+  @return: The string minus any html markup
+  @rtype: String  
+  """
+  # This is based upon code found at
+  # http://online.effbot.org/2003_08_01_archive.htm#20030811
+  # 
+  # It looks as if the original code is in the public domain
+  # per http://effbot.org/zone/copyright.htm
+  #
+  class Parser(htmllib.HTMLParser):
+    """
+    Private class for strip HTML
+    """  
+    def anchor_end(self):
+      self.anchor = None
+
+  class Formatter(formatter.AbstractFormatter):
+    """
+    Private class for strip HTML
+    """  
+    pass
+
+  class Writer(formatter.DumbWriter):
+    """
+    Private class for strip HTML
+    """  
+    def send_label_data(self, data):
+      """
+      """
+      self.send_flowing_data(data)
+      self.send_flowing_data(" ")
+
+  output = StringIO.StringIO()
+  parser = Parser(Formatter(Writer(output)))
+  parser.feed(htmlString)
+  parser.close()
+
+  return output.getvalue()

Modified: trunk/gnue-common/tests/utils_TextUtils.py
===================================================================
--- trunk/gnue-common/tests/utils_TextUtils.py  2005-08-22 14:31:33 UTC (rev 
7873)
+++ trunk/gnue-common/tests/utils_TextUtils.py  2005-08-23 19:32:54 UTC (rev 
7874)
@@ -34,7 +34,7 @@
   def setUp(self):
     self.shortText="Hello"
     self.longText="This is a longer line used to test the line wrap.  This is 
only a test"
-
+    
   def testLineWrap(self):
     """Check that the basic line wrap function properly wraps lines"""
     output = lineWrap(self.longText,27)
@@ -48,7 +48,30 @@
     
     assert lineWrap(self.longText, 27, alignment=ALIGN_RIGHT) == 
expectedResultRight, 'right alignment incorrect'
     assert lineWrap(self.longText, 27, alignment=ALIGN_CENTER) == 
expectedResultCenter, 'center alignment incorrect'
+
+
+  def testIntToRoman(self):
+    assert intToRoman(1999) == 'MCMXCIX', 'Roman numeral conversion failed'
+    assert intToRoman(2005) == 'MMV', 'Roman numeral conversion failed'
     
+  def testComify(self):
+    """Check comify function"""
+
+    assert comify(9999.25) == '9,999.25', 'comify failure'
+    assert comify(-9999.934, 2) == '-9,999.93', 'decimal truncation failure'
+    assert comify(-9999.934, 2, 1) == '(9,999.93)', 'parenthesis failure'
+
+        
+  def testStripHtml(self):
+    """Verify that stripHTML works"""
+    htmlText="""<body>
+<p>This is a test</p>
+</body>""" 
+
+    expectedText="""
+This is a test"""
+    assert stripHTML(htmlText) == expectedText, 'stripHTML failure'
+      
 def suite():
   suite = unittest.makeSuite(TextTestCase,'test')