migration-orm-fixes

migration/html2text/__init__.py

@@ -535,8 +535,7 @@ class HTML2Text(html.parser.HTMLParser):
 			if start:
 				if 'data-original-title' in attrs:
 					# WARNING: old discours specific code
-					if 'import Tooltip' not in self.outtextlist[0]: self.outtextlist.insert(0, 'import Tooltip from "$/components/Article/Tooltip"\n\n')
-					self.o('///%s///' % attrs['data-original-title'])
+					self.o('&&&%s&&&' % attrs['data-original-title'])
 				else:
 					if (
 						"href" in attrs 
@@ -1033,10 +1032,10 @@ class HTML2Text(html.parser.HTMLParser):
 		return result
 
 
-def html2text(html: str, baseurl: str = "", bodywidth: Optional[int] = None) -> str:
-	if bodywidth is None:
-		bodywidth = config.BODY_WIDTH
-	h = HTML2Text(baseurl=baseurl, bodywidth=bodywidth)
-
-	h = h.handle(html)
+def html2text(html: str, baseurl: str = "", bodywidth: Optional[int] = config.BODY_WIDTH) -> str:
+	h = html.strip() or ''
+	if h: 
+		h = HTML2Text(baseurl=baseurl, bodywidth=bodywidth)
+		h = h.handle(html.strip())
+		print('[html2text] %d bytes' % len(html))
 	return h

migration/html2text/config.py

@@ -7,7 +7,7 @@ UNICODE_SNOB = True
 TABLE_MARKER_FOR_PAD = "special_marker_for_table_padding"
 # Escape all special characters.  Output is less readable, but avoids
 # corner case formatting issues.
-ESCAPE_SNOB = False
+ESCAPE_SNOB = True
 
 # Put the links after each paragraph instead of at the end.
 LINKS_EACH_PARAGRAPH = False
@@ -46,10 +46,10 @@ IMAGES_AS_HTML = False
 IMAGES_TO_ALT = False
 IMAGES_WITH_SIZE = False
 IGNORE_EMPHASIS = False
-MARK_CODE = False
+MARK_CODE = True
 DECODE_ERRORS = "strict"
 DEFAULT_IMAGE_ALT = ""
-PAD_TABLES = False
+PAD_TABLES = True
 
 # Convert links with same href and text to <href> format
 # if they are absolute links