tagutils.py :  » Web-Services » python-xmltv » pytvgrab-lib-0.5.1 » lib » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Web Services » python xmltv 
python xmltv » pytvgrab lib 0.5.1 » lib » tagutils.py
#!/usr/bin/env python
# -*- coding: iso-8859-1 -*-

import sys
import string
from copy import copy
from tvgrab.grabexceptions import ParseError
import i18n
import re

class MalformedDataError( Exception ):
    contents=None
    exception=None
# MalformedDataError

def countInString(match,text):
    """
    Counts the occurence of the regular expression
    matches in some text
    """
    m = match.search(text)
    rv = 0
    while m:
        rv +=1
        m = match.search(text,m.end(0))
    return rv

def balanceTags(re_starttag,starttag,re_endtag,endtag,input):
    # Brutally tries to balance tags by adding
    # start tags at the beginning or end tags at the end
    # of input
    tablestart = countInString(re_starttag,input)
    tableend = countInString(re_endtag,input)
    if tablestart > tableend:
        #input = input + multiplyString(endtag,tablestart-tableend)
        input = input + endtag * (tablestart-tableend)
    elif tablestart < tableend:
        #input = multiplyString(starttag,tableend-tablestart) + input
        input = starttag*(tableend-tablestart) + input
    tablestart = countInString(re.compile("<table"),input)
    tableend = countInString(re.compile("</table>"),input)
    if tablestart!=tableend:
        print "error in balanceTags"
    return input
  
def findExtent(lines,startIndex,reStart,reStop):
  """
  Figures out and returns the extent of the current scoope
  starting at nextIndex and ending with a match of reStop
  """
  i = startIndex
  j = len(lines)
  startCount = 0
  endCount = 0
  match = reStart.search(lines,i)
  if match and match.start(0)==startIndex:
    startCount+=1
    i = match.end(0)
  else:
    assert "Dude, you did not set me up right!"
  while i<j and startCount!=endCount:
    matchStart = reStart.search(lines,i)
    matchEnd = reStop.search(lines,i)
    if matchStart and matchEnd:
      if matchStart.start(0) < matchEnd.start(0):
        i = matchStart.end(0)
        startCount+=1
      else:
        i = matchEnd.end(0)
        endCount+=1
    elif matchStart:
      # hm, seems to be an unbalance in the force
      i = matchStart.end(0)
      startCount+=1
    else:
      i = matchEnd.end(0)
      endCount+=1
  
  if endCount == startCount:
    return lines[startIndex:i]
  else:
    # Found EOF before tags were balanced
    return lines[startIndex:]

def blankHtml(lines,reStart,reStop,reTrigger):
  """
  Iterates though a html text looking for sections of the type
  reStart.*(<reStart>.*<reStop>)*.*reStop
  if reTrigger matches the innermost section, it will be replaced with spaces.
  Example:
  restart="<a",restop="</a>",retrigger="winner"
  txt=        "<a>bla bla<a>bla</a><a>a winner</a></a>" 
  will return "<a>bla bla<a>bla</a>               </a>"
  """ 

  queue = []
  index = 0
  length = len(lines)
  nextStart = None
  nextEnd = None
  while index < length:
    nextStart = reStart.search(lines,index)
    nextEnd = reStop.search(lines,index)
    if nextStart and nextEnd:
      if nextStart.start(0) < nextEnd.start(0):
        queue.append(nextStart.start(0))
        index = nextStart.end(0)
      else:
        range = (queue[-1],nextEnd.end(0))
        index = nextEnd.end(0)
        del queue[-1]
        if reTrigger.search(lines,range[0],range[1]):
          lines = lines[0:range[0]]+" "*(range[1]-range[0])+lines[range[1]:]
    elif nextStart:
      # Un-balanced tags
      queue.append(nextStart.start(0))
    elif nextEnd:
      range = (queue[-1],nextEnd.end(0))
      index = nextEnd.end(0)
      del queue[-1]
      if reTrigger.search(lines,range[0],range[1]):
        lines = lines[0:range[0]]+" "*(range[1]-range[0])+lines[range[1]:]
    else:
      index = length
  
  if reTrigger.search(lines):
    return " "*length
  else:
    return lines

def searchHtmlDF(lines,reStart,reStop,reTrigger):
  return searchHtml(lines, reStart,reStop,reTrigger,-1)
    
def searchHtmlBF(lines,reStart,reStop,reTrigger):
  return searchHtml(lines,reStart,reStop,reTrigger,1)

def searchHtml(lines,reStart,reStop,reTrigger,depth,matchOnRoot=False):
  """
  Iterates though a html text looking for sections of the type
  reStart.*(<reStart>.*<reStop>)*.*reStop
  if reTrigger matches the outermost section will be returned.
  depth is the maximum depth of the value returned.
  If it is positive the whole nested tree, blah ..... UPDATE COMMENT!
  
  Example:
  restart="<a",restop="</a>",retrigger="winner"
  txt= "<a>bla</a><a>bla bla<a>bla</a><a>a winner</a></a>" 
  will return "<a>bla bla<a>bla</a><a>a winner</a></a>"
  Note that this method returns data in breadth first mode.
  (it still searches the input top-down)
  In difference to searchHtmlDF nothing will be returned for
  matches on the root lvl. reStart must match at least once.
  """ 
  queue = []
  index = 0
  length = len(lines)
  nextStart = None
  nextEnd = None
  lastMatch = None
  while index < length:
    if (not nextStart) or (nextStart.start(0) < index):
      nextStart = reStart.search(lines,index)
    if (not nextEnd) or (nextEnd.start(0) < index):
      nextEnd = reStop.search(lines,index)
    if nextStart and nextEnd:
      if nextStart.start(0) < nextEnd.start(0):
        queue.append(nextStart.start(0))
        index = nextStart.end(0)
      else:
        range = (queue[-1],nextEnd.end(0))
        index = nextEnd.end(0)
        del queue[-1]
        if reTrigger.search(lines,range[0],range[1]):
          if not lastMatch:
            distanceToLastMatch = 0
          lastMatch = range
          distanceToLastMatch -= 1
          if depth==distanceToLastMatch or depth==len(queue)+1:
            return lines[lastMatch[0]:lastMatch[1]]
        #elif lastMatch:
          # we had a match, but we lost it in the last iteration
          #return lines[lastMatch[0]:lastMatch[1]]
          
    elif nextStart:
      # Un-balanced tags
      pe = ParseError( _( "%s could not be correctly parsed." ) % "Html" )
      pe.contents = lines
      raise pe
    elif nextEnd:
      range = (queue[-1],nextEnd.end(0))
      index = nextEnd.end(0)
      del queue[-1]
      if reTrigger.search(lines,range[0],range[1]):
        if not lastMatch:
            distanceToLastMatch = 0
        lastMatch = range
        distanceToLastMatch -= 1
        if depth==distanceToLastMatch or depth==len(queue)+1:
            return lines[lastMatch[0]:lastMatch[1]]
      #elif lastMatch:
      #  # we had a match, but we lost it in the last iteration
      #  return lines[lastMatch[0]:lastMatch[1]]  
    else:
      index = length
  # end while
  if matchOnRoot:
    if reTrigger.search(lines):
        return lines
    else:
        return ""
  else:
    return ""  
# --------------  Unit Tests  -------------- #
using_unittest2=False

try:
  import unittest2 as unittest
  using_unittest2=True
except:
  import unittest
    
class TagUtils_UnitTest(unittest.TestCase):

    def setUp(self):    
        # well formated test:
        self.i = """
        t011
        <d>
          t020t021
          <d>
            t1
          </d>
          t8
        </d>
        <d>
          t2
        </d>
        <d>
          t4
          <d>
            t3
            t021
          </d>
          t5
          <d>
            t6
          </d>
          t7
        </d>
        <d>
          <d>
            <d>
              t9
            </d>
          </d>
          t034
        </d>
        t010
        t022
        """
        
        noWhite=re.compile("\s+",re.S)    
        self.i = noWhite.sub("",self.i)
        
        start = re.compile("<d",re.S)
        end = re.compile("</d>")
        
        # searchHtmlDF
        
        trigger = re.compile("t1",re.S)
        self.o1 = searchHtmlDF(self.i,start,end,trigger)
        self.e1 = "<d>t1</d>"
        
        trigger = re.compile("t2",re.S)
        self.o2 = searchHtmlDF(self.i,start,end,trigger)
        self.e2 = "<d>t2</d>"
        
        trigger = re.compile("t3",re.S)
        self.o3 = searchHtmlDF(self.i,start,end,trigger)
        self.e3 = "<d>t3t021</d>"
        
        trigger = re.compile("t4",re.S)
        self.o4 = searchHtmlDF(self.i,start,end,trigger)
        self.e4 = "<d>t4<d>t3t021</d>t5<d>t6</d>t7</d>"
        
        trigger = re.compile("t5",re.S)
        self.o5 = searchHtmlDF(self.i,start,end,trigger)
        self.e5 = "<d>t4<d>t3t021</d>t5<d>t6</d>t7</d>"
        
        trigger = re.compile("t6",re.S)
        self.o6 = searchHtmlDF(self.i,start,end,trigger)
        self.e6 = "<d>t6</d>"
        
        trigger = re.compile("t7",re.S)
        self.o7 = searchHtmlDF(self.i,start,end,trigger)
        self.e7 = "<d>t4<d>t3t021</d>t5<d>t6</d>t7</d>"
        
        trigger = re.compile("t8",re.S)
        self.o8 = searchHtmlDF(self.i,start,end,trigger)
        self.e8 = "<d>t020t021<d>t1</d>t8</d>"
        
        trigger = re.compile("t9",re.S)
        self.o9 = searchHtmlDF(self.i,start,end,trigger)
        self.e9 = "<d>t9</d>"
        
        trigger = re.compile("t010",re.S)
        self.o10 = searchHtml(self.i,start,end,trigger,-1,True)
        self.e10 = "t011<d>t020t021<d>t1</d>t8</d><d>t2</d><d>t4<d>t3t021</d>t5<d>t6</d>t7</d><d><d><d>t9</d></d>t034</d>t010t022"
        
        trigger = re.compile("t011",re.S)
        self.o11 = searchHtml(self.i,start,end,trigger,-1,True)
        self.e11 = "t011<d>t020t021<d>t1</d>t8</d><d>t2</d><d>t4<d>t3t021</d>t5<d>t6</d>t7</d><d><d><d>t9</d></d>t034</d>t010t022"
        
        trigger = re.compile("t011",re.S)
        self.o12 = searchHtml(self.i,start,end,trigger,-1,False)
        self.e12 = ""
        
        # blankHtml
        
        trigger = re.compile("t020",re.S)
        self.o20 = blankHtml(self.i,start,end,trigger)
        self.e20 = "t011                          <d>t2</d><d>t4<d>t3t021</d>t5<d>t6</d>t7</d><d><d><d>t9</d></d>t034</d>t010t022"
        
        trigger = re.compile("t021",re.S)
        self.o21 = blankHtml(self.i,start,end,trigger)
        self.e21 = "t011                          <d>t2</d><d>t4             t5<d>t6</d>t7</d><d><d><d>t9</d></d>t034</d>t010t022"
        
        trigger = re.compile("t022",re.S)
        self.o22 = blankHtml(self.i,start,end,trigger)
        self.e22 = "                                                                                                             "
        
        # searchHtmlBF
        
        trigger = re.compile("t020",re.S)
        self.o30 = searchHtmlBF(self.i,start,end,trigger)
        self.e30 = "<d>t020t021<d>t1</d>t8</d>"
        
        trigger = re.compile("t022",re.S)
        self.o31 = searchHtmlBF(self.i,start,end,trigger)
        self.e31 = ""
        
        trigger = re.compile("t1",re.S)
        self.o32 = searchHtmlBF(self.i,start,end,trigger)
        self.e32 = "<d>t020t021<d>t1</d>t8</d>"
        
        trigger = re.compile("t021",re.S)
        self.o33 = searchHtmlBF(self.i,start,end,trigger)
        self.e33 = "<d>t020t021<d>t1</d>t8</d>"
        
        trigger = re.compile("t034",re.S)
        self.o34 = searchHtmlBF(self.i,start,end,trigger)
        self.e34 = "<d><d><d>t9</d></d>t034</d>" 
        pass
    
    # searchHtmlDF    
    def test01(self): v=self.o1; assert v == self.e1, v
    def test02(self): v=self.o2; assert v == self.e2, v
    def test03(self): v=self.o3; assert v == self.e3, v
    def test04(self): v=self.o4; assert v == self.e4, v
    def test05(self): v=self.o5; assert v == self.e5, v
    def test06(self): v=self.o6; assert v == self.e6, v
    def test07(self): v=self.o7; assert v == self.e7, v
    def test08(self): v=self.o8; assert v == self.e8, v
    def test09(self): v=self.o9; assert v == self.e9, v
    def test10(self): v=self.o10; assert v == self.e10, v
    def test11(self): v=self.o11; assert v == self.e11, v
    def test12(self): v=self.o12; assert v == self.e12, v
    # blankHtml
    def test20(self): v=self.o20; assert v == self.e20, v
    def test21(self): v=self.o21; assert v == self.e21, v
    def test22(self): v=self.o21; assert v == self.e21, v
    # searchHtmlBF
    def test30(self): v=self.o30; assert v == self.e30, v
    def test31(self): v=self.o31; assert v == self.e31, v
    def test32(self): v=self.o32; assert v == self.e32, v
    def test33(self): v=self.o33; assert v == self.e33, v
    
if using_unittest2 or __name__ == '__main__':
  unittest.main()
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.