Add Pypandoc for conversion from other formats

examples/markdown/markdown_syntax_ex1.md

@@ -0,0 +1,233 @@
+# h1 Heading
+## h2 Heading
+### h3 Heading
+#### h4 Heading
+##### h5 Heading
+###### h6 Heading
+
+
+## Horizontal Rules
+
+___
+
+---
+
+***
+
+
+## Typographic replacements
+
+Enable typographer option to see result.
+
+(c) (C) (r) (R) (tm) (TM) (p) (P) +-
+
+test.. test... test..... test?..... test!....
+
+!!!!!! ???? ,,  -- ---
+
+"Smartypants, double quotes" and 'single quotes'
+
+
+## Emphasis
+
+**This is bold text**
+
+__This is bold text__
+
+*This is italic text*
+
+_This is italic text_
+
+~~Strikethrough~~
+
+
+## Blockquotes
+
+
+> Blockquotes can also be nested...
+>> ...by using additional greater-than signs right next to each other...
+> > > ...or with spaces between arrows.
+
+
+## Lists
+
+Unordered
+
++ Create a list by starting a line with `+`, `-`, or `*`
++ Sub-lists are made by indenting 2 spaces:
+  - Marker character change forces new list start:
+    * Ac tristique libero volutpat at
+    + Facilisis in pretium nisl aliquet
+    - Nulla volutpat aliquam velit
++ Very easy!
+
+Ordered
+
+1. Lorem ipsum dolor sit amet
+2. Consectetur adipiscing elit
+3. Integer molestie lorem at massa
+
+
+1. You can use sequential numbers...
+1. ...or keep all the numbers as `1.`
+
+Start numbering with offset:
+
+57. foo
+1. bar
+
+
+## Code
+
+Inline `code`
+
+Indented code
+
+    // Some comments
+    line 1 of code
+    line 2 of code
+    line 3 of code
+
+
+Block code "fences"
+
+```
+Sample text here...
+```
+
+Syntax highlighting
+
+``` js
+var foo = function (bar) {
+  return bar++;
+};
+
+console.log(foo(5));
+```
+
+## Tables
+
+| Option | Description |
+| ------ | ----------- |
+| data   | path to data files to supply the data that will be passed into templates. |
+| engine | engine to be used for processing templates. Handlebars is the default. |
+| ext    | extension to be used for dest files. |
+
+Right aligned columns
+
+| Option | Description |
+| ------:| -----------:|
+| data   | path to data files to supply the data that will be passed into templates. |
+| engine | engine to be used for processing templates. Handlebars is the default. |
+| ext    | extension to be used for dest files. |
+
+
+## Links
+
+[link text](http://dev.nodeca.com)
+
+[link with title](http://nodeca.github.io/pica/demo/ "title text!")
+
+Autoconverted link https://github.com/nodeca/pica (enable linkify to see)
+
+
+## Images
+
+![Minion](https://octodex.github.com/images/minion.png)
+![Stormtroopocat](https://octodex.github.com/images/stormtroopocat.jpg "The Stormtroopocat")
+
+Like links, Images also have a footnote style syntax
+
+![Alt text][id]
+
+With a reference later in the document defining the URL location:
+
+[id]: https://octodex.github.com/images/dojocat.jpg  "The Dojocat"
+
+
+## Plugins
+
+The killer feature of `markdown-it` is very effective support of
+[syntax plugins](https://www.npmjs.org/browse/keyword/markdown-it-plugin).
+
+
+### [Emojies](https://github.com/markdown-it/markdown-it-emoji)
+
+> Classic markup: :wink: :cry: :laughing: :yum:
+>
+> Shortcuts (emoticons): :-) :-( 8-) ;)
+
+see [how to change output](https://github.com/markdown-it/markdown-it-emoji#change-output) with twemoji.
+
+
+### [Subscript](https://github.com/markdown-it/markdown-it-sub) / [Superscript](https://github.com/markdown-it/markdown-it-sup)
+
+- 19^th^
+- H~2~O
+
+
+### [\<ins>](https://github.com/markdown-it/markdown-it-ins)
+
+++Inserted text++
+
+
+### [\<mark>](https://github.com/markdown-it/markdown-it-mark)
+
+==Marked text==
+
+
+### [Footnotes](https://github.com/markdown-it/markdown-it-footnote)
+
+Footnote 1 link[^first].
+
+Footnote 2 link[^second].
+
+Inline footnote^[Text of inline footnote] definition.
+
+Duplicated footnote reference[^second].
+
+[^first]: Footnote **can have markup**
+
+    and multiple paragraphs.
+
+[^second]: Footnote text.
+
+
+### [Definition lists](https://github.com/markdown-it/markdown-it-deflist)
+
+Term 1
+
+:   Definition 1
+with lazy continuation.
+
+Term 2 with *inline markup*
+
+:   Definition 2
+
+        { some code, part of Definition 2 }
+
+    Third paragraph of definition 2.
+
+_Compact style:_
+
+Term 1
+  ~ Definition 1
+
+Term 2
+  ~ Definition 2a
+  ~ Definition 2b
+
+
+### [Abbreviations](https://github.com/markdown-it/markdown-it-abbr)
+
+This is HTML abbreviation example.
+
+It converts "HTML", but keep intact partial entries like "xxxHTMLyyy" and so on.
+
+*[HTML]: Hyper Text Markup Language
+
+### [Custom containers](https://github.com/markdown-it/markdown-it-container)
+
+::: warning
+*here be dragons*
+:::

jsondoc/bin/convert_jsondoc.py

@@ -1,30 +1,27 @@
 import argparse
-import json
+import pypandoc
+
 from jsondoc.convert.html import html_to_jsondoc
 from jsondoc.convert.markdown import jsondoc_to_markdown
-from jsondoc.serialize import jsondoc_dump_json, load_jsondoc
+from jsondoc.serialize import jsondoc_dump_json
 
 
 def convert_to_jsondoc(input_file, output_file=None, indent=None):
     # Read the input file
-    with open(input_file, "r") as file:
-        content = file.read()
 
     # Determine the file type based on extension
     file_extension = input_file.split(".")[-1].lower()
 
     if file_extension in ["html", "htm"]:
-        # Convert HTML to jsondoc
-        jsondoc = html_to_jsondoc(content)
-    elif file_extension in ["md", "markdown"]:
-        # For markdown, we'll first convert to HTML, then to jsondoc
-        # This is a placeholder as we don't have a direct markdown to jsondoc converter
-        html_content = markdown_to_html(
-            content
-        )  # You'll need to implement this function
-        jsondoc = html_to_jsondoc(html_content)
+        with open(input_file, "r") as file:
+            html_content = file.read()
     else:
-        raise ValueError(f"Unsupported file type: {file_extension}")
+        try:
+            html_content = pypandoc.convert_file(input_file, "html")
+        except RuntimeError as e:
+            raise ValueError(f"File type not supported for conversion: {input_file}")
+
+    jsondoc = html_to_jsondoc(html_content)
 
     # Serialize the jsondoc
     serialized_jsondoc = jsondoc_dump_json(jsondoc, indent=indent)
@@ -40,15 +37,6 @@ def convert_to_jsondoc(input_file, output_file=None, indent=None):
         # print(jsondoc_to_markdown(jsondoc))
 
 
-def markdown_to_html(markdown_content):
-    # Placeholder function for markdown to HTML conversion
-    # You'll need to implement this using a markdown library
-    # For example, you could use the `markdown` library:
-    # import markdown
-    # return markdown.markdown(markdown_content)
-    raise NotImplementedError("Markdown to HTML conversion not implemented")
-
-
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Convert files to jsondoc format")
     parser.add_argument("input_file", help="Path to the input file")
@@ -66,8 +54,12 @@ def markdown_to_html(markdown_content):
     )
     args = parser.parse_args()
 
-    convert_to_jsondoc(
-        args.input_file,
-        args.output_file,
-        indent=args.indent,
-    )
+    try:
+        convert_to_jsondoc(
+            args.input_file,
+            args.output_file,
+            indent=args.indent,
+        )
+    except ValueError as e:
+        print(e)
+        exit(1)

pyproject.toml

@@ -20,6 +20,7 @@ pydantic = "^2.7.2"
 thefuzz = "^0.22.1"
 jsonschema = "^4.23.0"
 bs4 = "^0.0.2"
+pypandoc = "^1.13"
 
 
 [tool.poetry.group.dev.dependencies]