1    #!/usr/bin/python
   2    
   3    # m2fchk.py
   4    # male-to-female markup check.
   5    
   6    # Required changes to your documents: put "<!--m2f-->" after a male
   7    # word (AND BEFORE ANY SPACES!) that needs to remain male due to
   8    # context.
   9    
  10    # Pertains to:
  11    # http://www.marxists.org/en/archive/spirkin/1983/dm/index.html
  12    #      ~/www.marxists.org/en/archive/spirkin/1983/dm/dm1983.tgz (XML)
  13    
  14    # The only output from this script should be <!ENTITY lines.
  15    
  16    # ------------------------------------------------------------------
  17    
  18    debug = 1
  19    debug = 0
  20    
  21    import fileinput
  22    import os
  23    import re
  24    import string
  25    
  26    regexp = {}
  27    regexp['other'] = {}
  28    regexp['other']['amp'] = re.compile('&')
  29    regexp['other']['alphas'] = re.compile('[' + string.letters + ']')
  30    
  31    regexp['other']['open_document_tag'] = re.compile('<(book|html)', re.I)
  32    regexp['other']['open_entity'] = re.compile('<!ENTITY', re.I)
  33    
  34    m2f_entities = ['~/www.marxists.org/en/archive/spirkin/1983/dm/dm1983.xml']
  35    
  36    
  37    
  38    m2f = {}
  39    m2f["he"] = "she"
  40    m2f["He"] = "She"
  41    
  42    m2f["him"] = "her"
  43    m2f["Him"] = "Her"
  44    m2f["his"] = "hers"
  45    m2f["His"] = "Hers"
  46    
  47    m2f["himself"] = "herself"
  48    m2f["Himself"] = "Herself"
  49    
  50    m2f["man"] = "woman"
  51    m2f["Man"] = "Woman"
  52    m2f["husband"] = "wife"
  53    m2f["Husband"] = "Wife"
  54    
  55    m2f["master"] = "mistress"
  56    m2f["Master"] = "Mistress"
  57    m2f["hero"] = "heroine"
  58    m2f["Hero"] = "Heroine"
  59    m2f["actor"] = "actress"
  60    m2f["Actor"] = "Actress"
  61    m2f["king"] = "queen"
  62    m2f["King"] = "Queen"
  63    
  64    # Get additional entities from external file(s):
  65    for filename in m2f_entities:
  66        f = open(os.path.expanduser(filename))
  67        while 1:
  68            d = f.readline()
  69            parts = string.split(d)
  70            for i in range(len(parts)):
  71                if regexp['other']['open_entity'].match(parts[i]):
  72                    m2f[parts[i+1]] = parts[i+2]
  73                    pass
  74                pass
  75            if regexp['other']['open_document_tag'].search(d): break
  76            pass
  77        f.close()
  78        pass
  79    
  80    regexp['m2f'] = {}
  81    for key in m2f.keys():
  82        regexp['m2f'][key] = re.compile(key)
  83    
  84        # Do not include female words:
  85        # regexp['m2f'][m2f[key]] = re.compile(m2f[key])
  86        pass
  87    
  88    def printit_fn(description, word, line):
  89        # Ignore marked words, e.g.: man,<!--m2f-->
  90        word = string.rstrip(word)
  91        s = '<!--m2f-->'
  92        if not word[-len(s):] == s:
  93            if debug: print description, word
  94            return 1
  95        else:
  96            return 0
  97        pass
  98    
  99    for line in fileinput.input():
 100        printit = 0
 101        words = string.split(line)
 102        for word in words:
 103            for exp in regexp['m2f'].keys():
 104                start = 0
 105                matchobj = regexp['m2f'][exp].search(word[start:])
 106                while matchobj:
 107    
 108                    # If either start or .start() is zero ...
 109                    if start - matchobj.start() == 0:
 110                        if len(matchobj.group()) == len(word):
 111    
 112                            printit = printit + printit_fn(
 113                                'Exact match:', word, line)
 114                            pass
 115                        else:
 116                            # If character after match is not a letter ...
 117                            if not regexp['other']['alphas'].match(
 118                                word[matchobj.end()]):
 119    
 120                                printit = printit + printit_fn(
 121                                    'Leading match:', word, line)
 122                                pass
 123                            pass
 124                        pass
 125    
 126                    # If character before match is not a letter ...
 127                    elif not regexp['other']['alphas'].match(
 128                        word[matchobj.start() - 1 + start]):
 129    
 130                        if len(word) == start + matchobj.end():
 131                            printit = printit + printit_fn(
 132                                'Trailing match:', word, line)
 133                            pass
 134    
 135                        # If character after match is not a letter ...
 136                        elif not regexp['other']['alphas'].match(
 137                            word[start + matchobj.end()]):
 138    
 139                            # If match isn't surrounded by &; ...
 140                            if not ('&' == word[matchobj.start() - 1 + start]
 141                                      and
 142                                      ';' == word[start + matchobj.end()]):
 143    
 144                                printit = printit + printit_fn(
 145                                    'Internal match:', word, line)
 146                                pass
 147                            pass
 148                        pass
 149    
 150                    start = start + matchobj.end()
 151                    matchobj = regexp['m2f'][exp].search(word[start:])
 152                    pass
 153                pass
 154            pass
 155    
 156        if not debug and printit > 0: print string.join([
 157            fileinput.filename(),
 158            ':',
 159            str(fileinput.filelineno()),
 160            ': ',
 161            string.rstrip(line)], '')
 162    
 163        # if fileinput.lineno() == 300: break
 164        # pass
 165    
 166    ###
 167    #