Program inefficiency?

[thebjorn]

On Sep 29, 8:32 pm, hall.j... at gmail.com wrote:
> It think he's saying it should look like this:
>
> # File: masseditor.py
>
> import re
> import os
> import time
>
> p1= re.compile('(href=|HREF=)+(.*)(#)+(.*)(\w\'\?-<:)+(.*)(">)+')
> p2= re.compile('(name=")+(.*)(\w\'\?-<:)+(.*)(">)+')
> p100= re.compile('(a name=)+(.*)(-)+(.*)(></a>)+')
> q1= r"\1\2\3\4_\6\7"
> q2= r"\1\2_\4\5"
>
> def massreplace():
>     editfile = open("C:\Program Files\Credit Risk Management\Masseditor
> \editfile.txt")
>     filestring = editfile.read()
>     filelist = filestring.splitlines()
>
>     for i in range(len(filelist)):
>         source = open(filelist[i])
>         starttext = source.read()
>
>         for i in range (13):
>             interimtext = p1.sub(q1, starttext)
>             interimtext= p2.sub(q2, interimtext)
>             interimtext= p100.sub(q2, interimtext)
>         source.close()
>         source = open(filelist[i],"w")
>         source.write(finaltext)
>         source.close()
>
> massreplace()
>
> I'll try that and see how it works...

Ok, if you want a single RE... How about:


  test = '''
  <a href="Web_Sites.htm#A Web Sites">
  <a name="A Web Sites"></a>
  <a
  href="Web_Sites.htm#A Web Sites">
  <a
  name="A Web Sites"></a>
  <a HREF="Web_Sites.htm#A Web                             Sites">
  <a name=Quoteless></a>
  <a name = "oo ps"></a>
  '''

  import re

  r = re.compile(r'''
      (?:href=['"][^#]+[#]([^"']+)["'])
    | (?:name=['"]?([^'">]+))
  ''', re.IGNORECASE | re.MULTILINE | re.DOTALL | re.VERBOSE)

  def zap_space(m):
      return m.group(0).replace(' ', '_')

  print r.sub(zap_space, test)

It prints out

  <a href="Web_Sites.htm#A_Web_Sites">
  <a name="A_Web_Sites"></a>
  <a
  href="Web_Sites.htm#A_Web_Sites">
  <a
  name="A_Web_Sites"></a>
  <a HREF="Web_Sites.htm#A_Web_____________________________Sites">
  <a name=Quoteless></a>
  <a name = "oo ps"></a>

-- bjorn