all-examples: files for handling pagified lines split with '/'

all-examples/split-sentence_handling/README.md

@@ -0,0 +1,5 @@
+`extract_split_sentences.py` extracts all lines split with `/` from `pagified.html`.
+The output is contained in `splits_unsplit.html`.
+
+`cursory_split.py` performs an initial parse of `splits_unsplit.html` to extract the contained sentences in each line. 
+The output, along with some manual additions, is contained in `splits.html`

all-examples/split-sentence_handling/cursory_split.py

@@ -0,0 +1,21 @@
+import re
+
+RE_SPLIT = re.compile(r'(<(u|small-caps)>[A-Za-z _\.]+ ?</(u|small-caps)>)( ?</(em|small-caps|u)>(<sub>i</sub>)? ?/ ?\*?<(em|small-caps|u)> ?)(<(u|small-caps)> ?[A-Za-z _\.]+</(u|small-caps)>(<sub>i</sub>)?)')
+
+if __name__ == '__main__':
+    splits = open('split_sentences_unsplit.html', 'r', encoding="utf-8").readlines()
+    all = []
+    for line in splits:
+        all.append(line)
+        if re.search(RE_SPLIT, line) is not None:
+            print(line)
+            split1 = re.sub(RE_SPLIT, r'\1', line)
+            print(split1)
+            split2 = re.sub(RE_SPLIT, r'\8', line)
+            print(split2)
+            all.append(split1)
+            all.append(split2)
+
+    splits_doc = ''.join(all)
+
+    print(splits_doc)

all-examples/split-sentence_handling/extract_split_sentences.py

@@ -0,0 +1,14 @@
+import re
+
+RE_SPLIT = re.compile(r'(>| )/(\*| |<)')
+
+if __name__ == '__main__':
+    pagified = open('../pagified.html', 'r', encoding="utf-8").readlines()
+    splits = []
+    for line in pagified:
+        if re.search(RE_SPLIT, line) is not None:
+            splits.append(line)
+
+    splits_doc = '\n'.join(splits)
+
+    print(splits_doc)