great punctuation handling

py-scripts.d/word-tags.py

@@ -0,0 +1,88 @@
+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):
+    # Only grab 0XX-canticle from `*.txt` file names
+    xmlfile = filename.split('.')[0] + '.xml'
+    tmpxmlfile = '.' + filename.split('.')[0] + '.tmp.xml'
+    with open(xmlfile,'w') as Cxml:
+        with open(tmpxmlfile,'w') as Cxmltmp:
+            with open(filename,'r') as Ctxt:
+                for spaced_line in Ctxt:
+                    # Use `~` as a placeholder for spaces later
+                    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
+                        # Catch single chars like `-`
+                        if L == 0:
+                            before_end_word_chars = word
+                            ending_punct_chars = ''
+                        # Catch single chars at end of line
+                        elif L == 1 and '\n' in word:
+                            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:
+                            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:]
+                        # Pad with spaces to ensure we get spaces between words
+                        # and importantly _around_ punctuation. We want:
+                        # `<w>Rispuosemi</w>: «<w>Non</w>` and not `<w>Rispuosemi</w>:«<w>Non</w>`.
+                        new_word = ' ' + starting_punct_chars + '<w>' + middle_word_chars + '</w>' + ending_punct_chars + ' '
+                        Cxmltmp.write(new_word)
+                Ctxt.close()
+            Cxmltmp.close()
+        with open(tmpxmlfile,'r') as Cxmltmp:
+            # Add space before opening word tag
+            def add_space(match):
+                match = match.group()
+                return re.sub('<w>', ' <w>', match)
+            for line in Cxmltmp:
+                # Swap double spaces from new_word with single spaces
+                line_spaced = re.sub('  ',' ',line)
+                # If there's a single space at the beginning of the line, delete it
+                line_spaced = line_spaced.lstrip(' ')
+                # Add three tabs at the beginning
+                line_spaced = re.sub('^','\t\t\t',line_spaced)
+                Cxml.write(line_spaced)
+            Cxmltmp.close()
+        os.remove(tmpxmlfile)
+        Cxml.close()
+
+for f in os.listdir(directory):
+    if f != 'word-tags.py' and f != '.word-tags.py.swp':
+        add_tags(f)
+    if f.endswith('.txt'):
+        os.remove(os.path.join(directory, f))