Verified Commit d026e458 authored by Jakob Moser's avatar Jakob Moser
Browse files

Add manual --document-type parameter

parent f7e6d557

pyproject.toml

+1 −1
Original line number Diff line number Diff line 
[project]

name = "coliverter"

version = "0.4.1"

version = "0.4.2"

authors = [

  { name="Jakob Moser", email="moser@cl.uni-heidelberg.de" },

]

src/coliverter/convert.py

+18 −6
Original line number Diff line number Diff line
@@ -5,6 +5,7 @@ from typing import Annotated 
from multiprocessing import Pool



from coliverter.documents.Document import Document

from coliverter.documents.DocumentType import DocumentType

from coliverter.files.FileFormat import FileFormat

from coliverter.cli.typer import typer

from coliverter.files.read import read
@@ -34,10 +35,13 @@ def _get_output_format( 




def _convert_single(

    markdown_path: Path | None, output_path: Path | None, output_format: FileFormat

    markdown_path: Path | None,

    output_path: Path | None,

    output_format: FileFormat,

    document_type: DocumentType | None,

) -> None:

    markdown = read(markdown_path)

    document = Document.from_markdown(markdown)

    document = Document.from_markdown(markdown, document_type)



    match output_format:

        case FileFormat.HTML:
@@ -51,6 +55,7 @@ def _convert_single_guessing_output_path( 
    markdown_dir_path: Path,

    output_dir_path: Path,

    output_format: FileFormat,

    document_type: DocumentType | None,

) -> None:

    guessed_out_file_path = output_dir_path / (

        markdown_file_path.relative_to(markdown_dir_path).with_suffix(
@@ -61,9 +66,7 @@ def _convert_single_guessing_output_path( 
    guessed_out_file_path.parent.mkdir(parents=True, exist_ok=True)



    _convert_single(

        markdown_file_path,

        guessed_out_file_path,

        output_format,

        markdown_file_path, guessed_out_file_path, output_format, document_type

    )
@@ -87,6 +90,12 @@ def convert( 
            help="Format of the output file. If None, infer from extension in output path. If inferring is not possible, default to html."

        ),

    ] = None,

    document_type: Annotated[

        DocumentType | None,

        Option(

            help="Type of the document. If None, guess it. Can be used to influence how content is transformed during conversion."

        ),

    ] = None,

) -> None:

    """

    Convert Markdown files into other formats, using the organization identity of Fachschaft Computerlinguistik.
@@ -109,7 +118,10 @@ def convert( 
                    repeat(markdown_path),

                    repeat(output_path),

                    repeat(definitely_output_format),

                    repeat(document_type),

                ),

            )

    else:

        _convert_single(markdown_path, output_path, definitely_output_format)
 
        _convert_single(

            markdown_path, output_path, definitely_output_format, document_type

        )

src/coliverter/documents/Document.py

+3 −2
Original line number Diff line number Diff line
@@ -41,13 +41,14 @@ class Document: 
            format=f"commonmark_x+{'+'.join(ACTIVE_MARKDOWN_EXTENSIONS)}",

            options=INPUT_OPTIONS,

        )

        document_type = maybe_type or DocumentType.guess(content)



        # Apply the transformations we want to do

        transformations = (insert_table_of_contents,)

        for transform in transformations:

            content = transform(content)

            content = transform(content, document_type)



        return cls(content=content, type=maybe_type or DocumentType.guess(content))

        return cls(content=content, type=document_type)



    @property

    def pdf(self) -> bytes:

src/coliverter/documents/transform/insert_table_of_contents.py

+8 −5
Original line number Diff line number Diff line
@@ -9,9 +9,7 @@ from coliverter.tree.Node import Node 
TOC_PLACEHOLDER = Para([Str("[["), Emph([Str("TOC")]), Str("]]")])





def _get_table_of_contents(document: Pandoc) -> BulletList:

    document_type = DocumentType.guess(document)



def _get_table_of_contents(document: Pandoc, document_type: DocumentType) -> BulletList:

    headers = tuple(

        element for element in pandoc.iter(document) if isinstance(element, Header)

    )
@@ -32,10 +30,15 @@ def _get_table_of_contents(document: Pandoc) -> BulletList: 
    return make_bullet_list(headers_tree)





def insert_table_of_contents(content: Pandoc) -> Pandoc:

def insert_table_of_contents(content: Pandoc, document_type: DocumentType) -> Pandoc:

    """

    Replace [[_TOC_]] with a table of contents whenever it appears in the content.



    This works in-place, i.e. `content` is modified. We nevertheless return it for convenience.



    :param content: The document contents

    :param document_type: The type of the document (necessary as it might require a special table of contents format)

    """

    return replace(content, TOC_PLACEHOLDER, _get_table_of_contents(content))
 
    return replace(

        content, TOC_PLACEHOLDER, _get_table_of_contents(content, document_type)

    )