epub converter: fix headings levels

src/data_objects.py

@@ -2,7 +2,7 @@ import re
 from typing import Union
 
 from ebooklib.epub import Section, Link
-
+from livecarta_config import LawCartaConfig
 
 """
 These are data structures which form mapping from NCX to python data structures.
@@ -10,13 +10,13 @@ These are data structures which form mapping from NCX to python data structures.
 
 
 class NavPoint:
-    def __init__(self, obj: Union[Link, Section]=None, ):
+    def __init__(self, obj: Union[Link, Section] = None, ):
         self.href, self.id = self.parse_href_id(obj)
         self.title = obj.title
 
     @staticmethod
     def parse_href_id(item: Union[Link, Section]):
-        reg = '(.+\..+\#)(.+)'
+        reg = r'(.+\..+\#)(.+)'
         match = re.search(reg, item.href)
         href, div_id = None, None
         if match:
@@ -24,7 +24,7 @@ class NavPoint:
             if match.group(1):
                 href = match.group(1)[:-1]
         else:
-            reg2 = '(.+\..+)'
+            reg2 = r'(.+\..+)'
             match2 = re.search(reg2, item.href)
             if match2 and match2.group(1):
                 href = match2.group(1)
@@ -39,6 +39,14 @@ class NavPoint:
 These are data structures which form mapping to livecarta json structure.
 """
 
+atom = lambda x: not isinstance(x, list)
+nil = lambda x: not x
+car = lambda x: x[0]
+cdr = lambda x: x[1:]
+cons = lambda x, y: x + y
+
+flatten = lambda x: [x] if atom(x) else x if nil(x) else cons(*map(flatten, [car(x), cdr(x)]))
+
 
 class ChapterItem:
     def __init__(self, title, content, sub_items):
@@ -46,16 +54,30 @@ class ChapterItem:
         self.content = content
         self.sub_items = sub_items
 
-    def to_dict(self):
-        tmp = []
+    def to_dict(self, lvl=1):
+        sub_dicts = []
         if self.sub_items:
             for i in self.sub_items:
-                tmp.append(i.to_dict())
+                sub_dicts.append(i.to_dict(lvl + 1))
+
+        if lvl > LawCartaConfig.SUPPORTED_LEVELS:
+            return {
+                "title": self.title,
+                "contents": [self.content] + [x['contents'] for x in sub_dicts],
+                "sub_items": []
+            }
+
+        if (lvl == LawCartaConfig.SUPPORTED_LEVELS) and sub_dicts:
+            return {
+                "title": self.title,
+                "contents": [self.content] + flatten([x['contents'] for x in sub_dicts]),
+                "sub_items": []
+            }
 
         return {
             "title": self.title,
             "contents": [self.content],
-            "sub_items": tmp
+            "sub_items": sub_dicts
         }
 
     def __str__(self):