groveling over a file for Q:: and A:: stmts

paul618 paul.nest.ce.pas at gmail.com
Tue Jul 24 09:50:22 CEST 2012


#!/usr/bin/env python
# grep_for_QA.py  I am only looking to isolate uniq Q:: and A:: stmts from my daily files
#
# note:  This algorithm will fail if there are any blank lines within the Q and A area of interest (a paragraph)

# D. Beazley is my fav documentation

import re, glob
import pprint as pp

sampledata = '''
A:: And Straight Street is playin on the Radio Free Tibet.  What are the chances, DTMB?  
Q:: About 1 in 518400, Professor.
A:: Correct!  Err, I thought it was 1:410400, but <i>close enough for jazz!</i>


'''

pattern0 = re.compile("Q::")
pattern1 = re.compile("A::")  # objects of interest can start with A:: ;; not alway Q::
END_OF_PARAGRAPH_pat = "\n\s*\n"

path = "/Users/paultaney/dailies2012/0722" # an example of real data set.

toggle = False
L = []
M = []

#file = open(path, "r")
try: 
    #for line in file.readlines():
    for line in sampledata:  
        try:
            # Later, I also need to treat Unicode -- and I am clueless.
  
            # falsestarts::
            #line.encode("utf8").decode('xxx', 'ignore')
            #line.encode("utf8", 'ignore') 
            #line.decode('8859')  
            #line.decode('8859')  # 8859, Latin-1 doesn't cover my  CJK pastings  AT ALL
            #line.decode('GB18030')  # 171006 -- ack
            #encoded_line = line  # xxx line.encode("utf8") 
            
            mo0 = re.search(pattern0, line)
            mo1 = re.search(pattern1, line)
            mo2 = re.search(END_OF_PARAGRAPH_pat, line)

            if mo0:
                if 1: print ("I see pattern 0")
                toggle = True
                if 1: print(line)
                M.append(mo0.group())

            if mo1:
                if 1: print ("I see pattern 1")
                toggle = True
                M.append(mo1.group())

            if mo2 and toggle:
                if 1: print ("I see pattern 2 AND toggle is set")
                # got one.  save it for uniqifying, and empty the container  
                toggle = False
                L.append(M)
                M = []

        except Exception as e:
            print("--- " + e + " ---")
        
except UnicodeDecodeError:
    #encoded_line = encoded_line.urlsafe_b64encode(re.replace("asdf", encoded_line))
    #line = re.sub(".+", "--- asdf ---", line)
    pass

L.sort
print (L)

# and what"s wrong with some of this, here!
#myHash = set(L)    # uniqify
#pp.pprint(myHash)  # july 23, 131001 hike!



More information about the Python-list mailing list