acrymble

# Given a list of n-grams, return a dictionary of KWICs,
# indexed by keyword.

def nGramsToKWICDict(ngrams):
    keyindex = len(ngrams[0]) // 2

    kwicdict = {}

    for k in ngrams:
      if k[keyindex] not in kwicdict:

acrymble

                amongst them a   black   there was one
                 first saw the   black   i turned to
              had observed the   black   in the mob
                  say who that   black   was no seeing
                       i saw a   black   at first but
                  swear to any   black   yes there is
                    swear to a   black   than to a
                                   ...

acrymble

# html-to-pretty-print.py
 
import obo
 
# create dictionary of n-grams
n = 7
url = 'http://www.oldbaileyonline.org/print.jsp?div=t17800628-33'
text = obo.webPageToText(url)
fullwordlist = obo.stripNonAlphaNum(text)
ngrams = obo.getNGrams(fullwordlist, n)

acrymble

# calculate the length of the n-gram
kwic = 'amongst them a black there was one'.split()
n = len(kwic)
print n
-> 7

# calculate the index position of the keyword
keyindex = n // 2
print keyindex
-> 3

acrymble

print ' '.join(kwic[(keyindex+1):])
-> there was one

acrymble

print '#' + str(kwic[keyindex]).center(len(kwic[keyindex])+6) + '#'
-> #   black   #

acrymble

width = 10
print '#' + ' '.join(kwic[:keyindex]).rjust(width*keyindex) + '#'
-> #                 amongst them a#

acrymble

# Given a KWIC, return a string that is formatted for
# pretty printing.

def prettyPrintKWIC(kwic):
    n = len(kwic)
    keyindex = n // 2
    width = 10
    outstring = ' '.join(kwic[:keyindex]).rjust(width*keyindex)
    outstring += str(kwic[keyindex]).center(len(kwic[keyindex])+6)
    outstring += ' '.join(kwic[(keyindex+1):])

acrymble

# html-to-kwic.py

import obo

# create dictionary of n-grams
n = 7
url = 'http://www.oldbaileyonline.org/print.jsp?div=t17800628-33'
text = obo.webPageToText(url)
fullwordlist = ('# ' * (n//2)).split()
fullwordlist += obo.stripNonAlphaNum(text)

acrymble

whole = wrapper % (program, now, url, url, body)