html: support highlighting

src/markdown_lib/common.py

@@ -216,6 +216,8 @@ def get_inline_tags(text: str, start_characters: list[str]) -> list[str]:
     "markdown_strict"
     # https://pandoc.org/chunkedhtml-demo/8.5-verbatim-code-blocks.html#extension-backtick_code_blocks
     "+backtick_code_blocks"
+    # https://pandoc.org/chunkedhtml-demo/8.21-non-default-extensions.html#extension-mark
+    "+mark"
     # https://pandoc.org/chunkedhtml-demo/8.9-tables.html#extension-pipe_tables
     "+pipe_tables"
     # https://pandoc.org/chunkedhtml-demo/8.12-inline-formatting.html#extension-strikeout
@@ -237,10 +239,11 @@ def markup_to_markdown(text: str, format_: str = "html") -> str:
         # some needed preprocessing
         soup = BeautifulSoup(text, "html.parser")
         markdown_lib.html_preprocessing.div_checklists(soup)
-        markdown_lib.html_preprocessing.handle_newlines_in_math(soup)
+        markdown_lib.html_preprocessing.highlighting(soup)
         markdown_lib.html_preprocessing.iframes_to_links(soup)
         markdown_lib.html_preprocessing.streamline_tables(soup)
         markdown_lib.html_preprocessing.synology_note_station_fix_img_src(soup)
+        markdown_lib.html_preprocessing.whitespace_in_math(soup)
         text = str(soup)
     text_md = pypandoc.convert_text(
         text,

src/markdown_lib/html_preprocessing.py

@@ -23,18 +23,10 @@ def div_checklists(soup: BeautifulSoup):
             child.name = "li"
 
 
-def handle_newlines_in_math(soup: BeautifulSoup):
-    """
-    - Escape unescaped newlines inside tex math blocks.
-    - Strip trailing (escaped) whitespace.
-    """
-    for annotation in soup.find_all("annotation"):
-        if (encoding := annotation.attrs.get("encoding")) != "application/x-tex":
-            LOGGER.debug(f'Unsupported annotation encoding "{encoding}"')
-            continue
-        annotation.string = annotation.string.rstrip("\\" + string.whitespace).replace(
-            "\n\n", "\n\\\\\n"
-        )
+def highlighting(soup: BeautifulSoup):
+    """Remove all attributes and enable the "mark" extension to get highlighting."""
+    for mark in soup.find_all("mark"):
+        mark.attrs = {}
 
 
 def iframes_to_links(soup: BeautifulSoup):
@@ -186,3 +178,17 @@ def streamline_tables(soup: BeautifulSoup):
             body.unwrap()
 
         table.attrs = {}
+
+
+def whitespace_in_math(soup: BeautifulSoup):
+    """
+    - Escape unescaped newlines inside tex math blocks.
+    - Strip trailing (escaped) whitespace.
+    """
+    for annotation in soup.find_all("annotation"):
+        if (encoding := annotation.attrs.get("encoding")) != "application/x-tex":
+            LOGGER.debug(f'Unsupported annotation encoding "{encoding}"')
+            continue
+        annotation.string = annotation.string.rstrip("\\" + string.whitespace).replace(
+            "\n\n", "\n\\\\\n"
+        )