Add <w></w> tags w/o punct

py-scripts/word-tags.py

@@ -0,0 +1,81 @@
+import re
+import os
+
+"""
+Replace every space with a special character and then re-replace them?  You lose the space between `:«` with current method.
+"""
+
+path = __file__
+
+directory = os.path.abspath(os.getcwd())
+
+def add_tags(filename):
+    """
+    The filenames should be <canticle>-<num>.txt
+    """
+    print('Adding tags to: ' + filename)
+    xmlfile = filename + '.xml'
+    tmpxmlfile = filename + '.tmp.xml'
+    with open(xmlfile,'w') as Ixml:
+        with open(tmpxmlfile,'w') as Ixmltmp:
+            with open(filename,'r') as Itxt:
+                for spaced_line in Itxt:
+                    line = re.sub(' ','~',spaced_line)
+                    words = line.split('~')
+                    for i in range(len(words)):
+                        word = words[i]
+                        # Iterate from ending to beginning of word
+                        L = len(word) - 1
+                        if L == 0:
+                            before_end_word_chars = word
+                            ending_punct_chars = ''
+                        elif L == 1 and '\n' in word:
+                            print('Got HERE')
+                            before_end_word_chars = word.rstrip()
+                            ending_punct_chars = '\n'
+                        else:
+                            print('Got to <- with: ' + word + ' and this L: ' + str(L) + ' in ' + filename)
+                            # we need `word[L] != '-'` because there are some words like `-:`
+                            while word[L] != '’' and word[L] != '-' and not word[L].isalpha():
+                                L-=1
+                            else:
+                                ending_punct_begin_index = L + 1
+                                ending_punct_chars = word[ending_punct_begin_index:]
+                                before_end_word_chars = word[:ending_punct_begin_index]
+                        # Iterate from start to remainder of word
+                        L = len(word) - 1
+                        if L == 0:
+                            middle_word_chars = word
+                            starting_punct_chars = ''
+                        elif L == 1 and '\n' in word:
+                            print('Got HERE!!!')
+                            middle_word_chars = word.rstrip()
+                            starting_punct_chars = ''
+                        else:
+                            print('Got -> with this word: ' + word + ' and this L: ' + str(L) + ' in ' + filename)
+                            while word[-L - 1] != '‘' and word[-L - 1] != '’' and word[L] != '-' and not word[-L - 1].isalpha():
+                                L-=1
+                            else:
+                                starting_punct_end_index = -L - 1
+                                starting_punct_chars = word[:starting_punct_end_index]
+                                middle_word_chars = before_end_word_chars[-L-1:]
+                                #print(starting_punct_chars + ' ' + middle_word_chars + ' ' + ending_punct_chars + ' ' + str(L))
+                        new_word = starting_punct_chars + '<w>' + middle_word_chars + '</w>' + ending_punct_chars
+                        Ixmltmp.write(new_word)
+                Itxt.close()
+            Ixmltmp.close()
+        with open(tmpxmlfile,'r') as Ixmltmp:
+            for line in Ixmltmp:
+                #line_spaced = re.sub(pattern,repl,string,count=0,flags=0)
+                def add_space(match):
+                    match = match.group()
+                    return re.sub('<w>', ' <w>', match)
+                line_spaced = re.sub('</w>.*?<w>', add_space, line)
+                Ixml.write(line_spaced)
+            Ixmltmp.close()
+        os.remove(tmpxmlfile)
+        Ixml.close()
+
+for f in os.listdir(directory):
+    if f != 'word-tags.py' and f != '.word-tags.py.swp':
+        add_tags(f)