strip headings by default

src/formats/cacher.py

@@ -8,6 +8,7 @@
 import common
 import converter
 import intermediate_format as imf
+import markdown_lib.common
 
 
 class Converter(converter.BaseConverter):
@@ -23,9 +24,11 @@ def convert_note(self, file_: dict, notebook: imf.Notebook, tags: imf.Tags):
             return
         title = Path(file_["filename"]).stem
         self.logger.debug(f'Converting note "{title}"')
+
+        _, body = markdown_lib.common.split_title_from_body(file_["content"])
         note_imf = imf.Note(
             title,
-            file_["content"],
+            body,
             created=dt.datetime.fromisoformat(file_["createdAt"]),
             updated=dt.datetime.fromisoformat(file_["updatedAt"]),
             source_application=self.format,

src/formats/joplin.py

@@ -55,7 +55,7 @@ class Converter(converter.BaseConverter):
 
     @common.catch_all_exceptions
     def convert_note(self, markdown: str, metadata_json: dict, parent_id_note_map):
-        title, body = markdown_lib.common.split_h1_title_from_body(markdown)
+        title, body = markdown_lib.common.split_title_from_body(markdown, h1=False)
         self.logger.debug(f'Converting note "{title}"')
         note_imf = imf.Note(
             title.strip(),

src/formats/notion.py

@@ -104,13 +104,12 @@ def convert_note(
 
         self.logger.debug(f'Converting note "{title}"')
         body = item.read_text(encoding="utf-8")
-        if item.suffix.lower() == ".md":
-            # first line is title, second is whitespace
-            body = "\n".join(item.read_text(encoding="utf-8").split("\n")[2:])
-        else:  # html
+        if item.suffix.lower() == ".html":
+            # html, else markdown
             body = markdown_lib.common.markup_to_markdown(
                 body, custom_filter=[markdown_lib.html_filter.notion_streamline_lists]
             )
+        _, body = markdown_lib.common.split_title_from_body(body)
 
         # find links
         resources, note_links = self.handle_markdown_links(body, item)

src/formats/simplenote.py

@@ -16,8 +16,8 @@ class Converter(converter.BaseConverter):
     @common.catch_all_exceptions
     def convert_note(self, note_simplenote):
         # title is the first line
-        title, body = markdown_lib.common.split_h1_title_from_body(
-            note_simplenote["content"]
+        title, body = markdown_lib.common.split_title_from_body(
+            note_simplenote["content"], h1=False
         )
         self.logger.debug(f'Converting note "{title}"')
 

src/formats/textbundle.py

@@ -41,9 +41,11 @@ def convert_note(self, file_: Path, parent_notebook: imf.Notebook):
         title = file_.parent.stem
         self.logger.debug(f'Converting note "{title}"')
 
-        note_imf = imf.Note(
-            title, file_.read_text(encoding="utf-8"), source_application=self.format
+        # title = first line header
+        _, body = markdown_lib.common.split_title_from_body(
+            file_.read_text(encoding="utf-8")
         )
+        note_imf = imf.Note(title, body, source_application=self.format)
         note_imf.tags = [
             imf.Tag(tag)
             for tag in markdown_lib.common.get_inline_tags(note_imf.body, ["#"])

src/markdown_lib/common.py

@@ -17,14 +17,29 @@
 LOGGER = logging.getLogger("jimmy")
 
 
-def split_h1_title_from_body(markdown_: str) -> tuple[str, str]:
-    # TODO: doctest
-    try:
-        title, body = markdown_.split("\n", maxsplit=1)
-    except ValueError:
-        title = markdown_
-        body = ""
-    return title.lstrip("# "), body.lstrip()
+def split_title_from_body(markdown_: str, h1: bool = True) -> tuple[str, str]:
+    r"""
+    >>> split_title_from_body("# heading\n\n b")
+    ('heading', 'b')
+    >>> split_title_from_body("heading\n\n b")
+    ('', 'heading\n\n b')
+    >>> split_title_from_body("heading\n\n b", h1=False)
+    ('heading', 'b')
+    >>> split_title_from_body("😄\n\n# heading")
+    ('', '😄\n\n# heading')
+    """
+    if markdown_.startswith("# ") or not h1:
+        try:
+            title, body = markdown_.split("\n", maxsplit=1)
+            title = title.lstrip("# ")
+            body = body.lstrip()
+        except ValueError:
+            title = markdown_
+            body = ""
+    else:
+        title = ""
+        body = markdown_
+    return title, body
 
 
 @dataclass