SYMBOL INDEX (383 symbols across 52 files)

FILE: packages/markitdown-mcp/src/markitdown_mcp/__main__.py
  function convert_to_markdown (line 21) | async def convert_to_markdown(uri: str) -> str:
  function check_plugins_enabled (line 26) | def check_plugins_enabled() -> bool:
  function create_starlette_app (line 34) | def create_starlette_app(mcp_server: Server, *, debug: bool = False) -> ...
  function main (line 82) | def main():

FILE: packages/markitdown-ocr/src/markitdown_ocr/_docx_converter_with_ocr.py
  class DocxConverterWithOCR (line 33) | class DocxConverterWithOCR(HtmlConverter):
    method __init__ (line 39) | def __init__(self, ocr_service: Optional[LLMVisionOCRService] = None):
    method accepts (line 44) | def accepts(
    method convert (line 63) | def convert(
    method _extract_and_ocr_images (line 126) | def _extract_and_ocr_images(
    method _inject_placeholders (line 160) | def _inject_placeholders(

FILE: packages/markitdown-ocr/src/markitdown_ocr/_ocr_service.py
  class OCRResult (line 14) | class OCRResult:
  class LLMVisionOCRService (line 23) | class LLMVisionOCRService:
    method __init__ (line 26) | def __init__(
    method extract_text (line 48) | def extract_text(

FILE: packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py
  function _extract_images_from_page (line 28) | def _extract_images_from_page(page: Any) -> list[dict]:
  class PdfConverterWithOCR (line 129) | class PdfConverterWithOCR(DocumentConverter):
    method __init__ (line 135) | def __init__(self, ocr_service: Optional[LLMVisionOCRService] = None):
    method accepts (line 139) | def accepts(
    method convert (line 158) | def convert(
    method _extract_page_images (line 313) | def _extract_page_images(self, pdf_bytes: io.BytesIO, page_num: int) -...
    method _ocr_full_pages (line 340) | def _ocr_full_pages(

FILE: packages/markitdown-ocr/src/markitdown_ocr/_plugin.py
  function register_converters (line 19) | def register_converters(markitdown: MarkItDown, **kwargs: Any) -> None:

FILE: packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py
  class PptxConverterWithOCR (line 27) | class PptxConverterWithOCR(DocumentConverter):
    method __init__ (line 30) | def __init__(self, ocr_service: Optional[LLMVisionOCRService] = None):
    method accepts (line 35) | def accepts(
    method convert (line 54) | def convert(
    method _is_picture (line 188) | def _is_picture(self, shape):
    method _is_table (line 196) | def _is_table(self, shape):
    method _convert_table_to_markdown (line 201) | def _convert_table_to_markdown(self, table, **kwargs):
    method _convert_chart_to_markdown (line 222) | def _convert_chart_to_markdown(self, chart):

FILE: packages/markitdown-ocr/src/markitdown_ocr/_xlsx_converter_with_ocr.py
  class XlsxConverterWithOCR (line 27) | class XlsxConverterWithOCR(DocumentConverter):
    method __init__ (line 33) | def __init__(self, ocr_service: Optional[LLMVisionOCRService] = None):
    method accepts (line 38) | def accepts(
    method convert (line 57) | def convert(
    method _convert_standard (line 88) | def _convert_standard(
    method _convert_with_ocr (line 108) | def _convert_with_ocr(
    method _extract_and_ocr_sheet_images (line 149) | def _extract_and_ocr_sheet_images(
    method _column_number_to_letter (line 217) | def _column_number_to_letter(n: int) -> str:

FILE: packages/markitdown-ocr/tests/test_docx_converter.py
  class MockOCRService (line 32) | class MockOCRService:
    method extract_text (line 33) | def extract_text(  # noqa: ANN101
  function svc (line 40) | def svc() -> MockOCRService:
  function _convert (line 44) | def _convert(filename: str, ocr_service: MockOCRService) -> str:
  function test_docx_image_start (line 60) | def test_docx_image_start(svc: MockOCRService) -> None:
  function test_docx_image_middle (line 75) | def test_docx_image_middle(svc: MockOCRService) -> None:
  function test_docx_image_end (line 92) | def test_docx_image_end(svc: MockOCRService) -> None:
  function test_docx_multiple_images (line 108) | def test_docx_multiple_images(svc: MockOCRService) -> None:
  function test_docx_multipage (line 125) | def test_docx_multipage(svc: MockOCRService) -> None:
  function test_docx_complex_layout (line 152) | def test_docx_complex_layout(svc: MockOCRService) -> None:
  function test_inject_placeholders_single_image (line 171) | def test_inject_placeholders_single_image() -> None:
  function test_inject_placeholders_two_images_sequential_tokens (line 180) | def test_inject_placeholders_two_images_sequential_tokens() -> None:
  function test_inject_placeholders_no_img_tag_appends_at_end (line 194) | def test_inject_placeholders_no_img_tag_appends_at_end() -> None:
  function test_inject_placeholders_empty_map_leaves_html_unchanged (line 202) | def test_inject_placeholders_empty_map_leaves_html_unchanged() -> None:
  function test_docx_no_ocr_service_no_tags (line 215) | def test_docx_no_ocr_service_no_tags() -> None:

FILE: packages/markitdown-ocr/tests/test_pdf_converter.py
  class MockOCRService (line 36) | class MockOCRService:
    method extract_text (line 37) | def extract_text(
  function svc (line 46) | def svc() -> MockOCRService:
  function _convert (line 50) | def _convert(filename: str, ocr_service: MockOCRService) -> str:
  function test_pdf_image_start (line 66) | def test_pdf_image_start(svc: MockOCRService) -> None:
  function test_pdf_image_middle (line 82) | def test_pdf_image_middle(svc: MockOCRService) -> None:
  function test_pdf_image_end (line 100) | def test_pdf_image_end(svc: MockOCRService) -> None:
  function test_pdf_multiple_images (line 117) | def test_pdf_multiple_images(svc: MockOCRService) -> None:
  function test_pdf_complex_layout (line 134) | def test_pdf_complex_layout(svc: MockOCRService) -> None:
  function test_pdf_multipage (line 151) | def test_pdf_multipage(svc: MockOCRService) -> None:
  function test_pdf_scanned_invoice (line 167) | def test_pdf_scanned_invoice(svc: MockOCRService) -> None:
  function test_pdf_scanned_meeting_minutes (line 171) | def test_pdf_scanned_meeting_minutes(svc: MockOCRService) -> None:
  function test_pdf_scanned_minimal (line 175) | def test_pdf_scanned_minimal(svc: MockOCRService) -> None:
  function test_pdf_scanned_sales_report (line 179) | def test_pdf_scanned_sales_report(svc: MockOCRService) -> None:
  function test_pdf_scanned_report (line 183) | def test_pdf_scanned_report(svc: MockOCRService) -> None:
  function test_pdf_scanned_fallback_format (line 197) | def test_pdf_scanned_fallback_format(svc: MockOCRService) -> None:
  function test_pdf_no_ocr_service_no_tags (line 226) | def test_pdf_no_ocr_service_no_tags() -> None:

FILE: packages/markitdown-ocr/tests/test_pptx_converter.py
  class MockOCRService (line 36) | class MockOCRService:
    method extract_text (line 37) | def extract_text(
  function svc (line 46) | def svc() -> MockOCRService:
  function _convert (line 50) | def _convert(filename: str, ocr_service: MockOCRService) -> str:
  function test_pptx_image_start (line 66) | def test_pptx_image_start(svc: MockOCRService) -> None:
  function test_pptx_image_middle (line 80) | def test_pptx_image_middle(svc: MockOCRService) -> None:
  function test_pptx_image_end (line 96) | def test_pptx_image_end(svc: MockOCRService) -> None:
  function test_pptx_multiple_images (line 111) | def test_pptx_multiple_images(svc: MockOCRService) -> None:
  function test_pptx_complex_layout (line 126) | def test_pptx_complex_layout(svc: MockOCRService) -> None:
  function test_pptx_no_ocr_service_no_tags (line 140) | def test_pptx_no_ocr_service_no_tags() -> None:

FILE: packages/markitdown-ocr/tests/test_xlsx_converter.py
  class MockOCRService (line 37) | class MockOCRService:
    method extract_text (line 38) | def extract_text(
  function svc (line 47) | def svc() -> MockOCRService:
  function _convert (line 51) | def _convert(filename: str, ocr_service: MockOCRService) -> str:
  function test_xlsx_image_start (line 67) | def test_xlsx_image_start(svc: MockOCRService) -> None:
  function test_xlsx_image_middle (line 92) | def test_xlsx_image_middle(svc: MockOCRService) -> None:
  function test_xlsx_image_end (line 127) | def test_xlsx_image_end(svc: MockOCRService) -> None:
  function test_xlsx_multiple_images (line 166) | def test_xlsx_multiple_images(svc: MockOCRService) -> None:
  function test_xlsx_complex_layout (line 201) | def test_xlsx_complex_layout(svc: MockOCRService) -> None:
  function test_xlsx_no_ocr_service_no_tags (line 241) | def test_xlsx_no_ocr_service_no_tags() -> None:

FILE: packages/markitdown-sample-plugin/src/markitdown_sample_plugin/_plugin.py
  function register_converters (line 25) | def register_converters(markitdown: MarkItDown, **kwargs):
  class RtfConverter (line 34) | class RtfConverter(DocumentConverter):
    method accepts (line 39) | def accepts(
    method convert (line 57) | def convert(

FILE: packages/markitdown-sample-plugin/tests/test_sample_plugin.py
  function test_converter (line 15) | def test_converter() -> None:
  function test_markitdown (line 30) | def test_markitdown() -> None:

FILE: packages/markitdown/src/markitdown/__main__.py
  function main (line 13) | def main():
  function _handle_output (line 203) | def _handle_output(args, result: DocumentConverterResult):
  function _exit_with_error (line 217) | def _exit_with_error(message: str):

FILE: packages/markitdown/src/markitdown/_base_converter.py
  class DocumentConverterResult (line 5) | class DocumentConverterResult:
    method __init__ (line 8) | def __init__(
    method text_content (line 28) | def text_content(self) -> str:
    method text_content (line 33) | def text_content(self, markdown: str):
    method __str__ (line 37) | def __str__(self) -> str:
  class DocumentConverter (line 42) | class DocumentConverter:
    method accepts (line 45) | def accepts(
    method convert (line 84) | def convert(

FILE: packages/markitdown/src/markitdown/_exceptions.py
  class MarkItDownException (line 11) | class MarkItDownException(Exception):
  class MissingDependencyException (line 19) | class MissingDependencyException(MarkItDownException):
  class UnsupportedFormatException (line 34) | class UnsupportedFormatException(MarkItDownException):
  class FailedConversionAttempt (line 42) | class FailedConversionAttempt(object):
    method __init__ (line 47) | def __init__(self, converter: Any, exc_info: Optional[tuple] = None):
  class FileConversionException (line 52) | class FileConversionException(MarkItDownException):
    method __init__ (line 58) | def __init__(

FILE: packages/markitdown/src/markitdown/_markitdown.py
  function _load_plugins (line 65) | def _load_plugins() -> Union[None, List[Any]]:
  class ConverterRegistration (line 86) | class ConverterRegistration:
  class MarkItDown (line 93) | class MarkItDown:
    method __init__ (line 97) | def __init__(
    method enable_builtins (line 140) | def enable_builtins(self, **kwargs) -> None:
    method enable_plugins (line 232) | def enable_plugins(self, **kwargs) -> None:
    method convert (line 252) | def convert(
    method convert_local (line 302) | def convert_local(
    method convert_stream (line 339) | def convert_stream(
    method convert_url (line 386) | def convert_url(
    method convert_uri (line 405) | def convert_uri(
    method convert_response (line 466) | def convert_response(
    method _convert (line 538) | def _convert(
    method register_page_converter (line 633) | def register_page_converter(self, converter: DocumentConverter) -> None:
    method register_converter (line 641) | def register_converter(
    method _get_stream_info_guesses (line 673) | def _get_stream_info_guesses(
    method _normalize_charset (line 774) | def _normalize_charset(self, charset: str | None) -> str | None:

FILE: packages/markitdown/src/markitdown/_stream_info.py
  class StreamInfo (line 6) | class StreamInfo:
    method copy_and_update (line 20) | def copy_and_update(self, *args, **kwargs):

FILE: packages/markitdown/src/markitdown/_uri_utils.py
  function file_uri_to_path (line 8) | def file_uri_to_path(file_uri: str) -> Tuple[str | None, str]:
  function parse_data_uri (line 19) | def parse_data_uri(uri: str) -> Tuple[str | None, Dict[str, str], bytes]:

FILE: packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py
  function load (line 43) | def load(stream):
  function load_string (line 49) | def load_string(string):
  function escape_latex (line 55) | def escape_latex(strs):
  function get_val (line 68) | def get_val(key, default=None, store=CHR):
  class Tag2Method (line 75) | class Tag2Method(object):
    method call_method (line 76) | def call_method(self, elm, stag=None):
    method process_children_list (line 86) | def process_children_list(self, elm, include=None):
    method process_children_dict (line 103) | def process_children_dict(self, elm, include=None):
    method process_children (line 112) | def process_children(self, elm, include=None):
    method process_unknow (line 123) | def process_unknow(self, elm, stag):
  class Pr (line 127) | class Pr(Tag2Method):
    method __init__ (line 136) | def __init__(self, elm):
    method __str__ (line 140) | def __str__(self):
    method __unicode__ (line 143) | def __unicode__(self):
    method __getattr__ (line 146) | def __getattr__(self, name):
    method do_brk (line 149) | def do_brk(self, elm):
    method do_common (line 153) | def do_common(self, elm):
  class oMath2Latex (line 170) | class oMath2Latex(Tag2Method):
    method __init__ (line 179) | def __init__(self, element):
    method __str__ (line 182) | def __str__(self):
    method __unicode__ (line 185) | def __unicode__(self):
    method process_unknow (line 188) | def process_unknow(self, elm, stag):
    method latex (line 197) | def latex(self):
    method do_acc (line 200) | def do_acc(self, elm):
    method do_bar (line 210) | def do_bar(self, elm):
    method do_d (line 219) | def do_d(self, elm):
    method do_spre (line 234) | def do_spre(self, elm):
    method do_sub (line 240) | def do_sub(self, elm):
    method do_sup (line 244) | def do_sup(self, elm):
    method do_f (line 248) | def do_f(self, elm):
    method do_func (line 257) | def do_func(self, elm):
    method do_fname (line 265) | def do_fname(self, elm):
    method do_groupchr (line 281) | def do_groupchr(self, elm):
    method do_rad (line 290) | def do_rad(self, elm):
    method do_eqarr (line 302) | def do_eqarr(self, elm):
    method do_limlow (line 312) | def do_limlow(self, elm):
    method do_limupp (line 323) | def do_limupp(self, elm):
    method do_lim (line 330) | def do_lim(self, elm):
    method do_m (line 336) | def do_m(self, elm):
    method do_mr (line 348) | def do_mr(self, elm):
    method do_nary (line 356) | def do_nary(self, elm):
    method do_r (line 369) | def do_r(self, elm):

FILE: packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py
  function _convert_omath_to_latex (line 33) | def _convert_omath_to_latex(tag: Tag) -> str:
  function _get_omath_tag_replacement (line 52) | def _get_omath_tag_replacement(tag: Tag, block: bool = False) -> Tag:
  function _replace_equations (line 74) | def _replace_equations(tag: Tag):
  function _pre_process_math (line 99) | def _pre_process_math(content: bytes) -> bytes:
  function pre_process_docx (line 118) | def pre_process_docx(input_docx: BinaryIO) -> BinaryIO:

FILE: packages/markitdown/src/markitdown/converters/_audio_converter.py
  class AudioConverter (line 23) | class AudioConverter(DocumentConverter):
    method accepts (line 28) | def accepts(
    method convert (line 46) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_bing_serp_converter.py
  class BingSerpConverter (line 23) | class BingSerpConverter(DocumentConverter):
    method accepts (line 29) | def accepts(
    method convert (line 57) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_csv_converter.py
  class CsvConverter (line 15) | class CsvConverter(DocumentConverter):
    method __init__ (line 20) | def __init__(self):
    method accepts (line 23) | def accepts(
    method convert (line 38) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
  class AzureKeyCredential (line 28) | class AzureKeyCredential:
  class TokenCredential (line 31) | class TokenCredential:
  class DocumentIntelligenceClient (line 34) | class DocumentIntelligenceClient:
  class AnalyzeDocumentRequest (line 37) | class AnalyzeDocumentRequest:
  class AnalyzeResult (line 40) | class AnalyzeResult:
  class DocumentAnalysisFeature (line 43) | class DocumentAnalysisFeature:
  class DefaultAzureCredential (line 46) | class DefaultAzureCredential:
  class DocumentIntelligenceFileType (line 55) | class DocumentIntelligenceFileType(str, Enum):
  function _get_mime_type_prefixes (line 71) | def _get_mime_type_prefixes(types: List[DocumentIntelligenceFileType]) -...
  function _get_file_extensions (line 104) | def _get_file_extensions(types: List[DocumentIntelligenceFileType]) -> L...
  class DocumentIntelligenceConverter (line 130) | class DocumentIntelligenceConverter(DocumentConverter):
    method __init__ (line 133) | def __init__(
    method accepts (line 189) | def accepts(
    method _analysis_features (line 207) | def _analysis_features(self, stream_info: StreamInfo) -> List[str]:
    method convert (line 237) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_docx_converter.py
  class DocxConverter (line 31) | class DocxConverter(HtmlConverter):
    method __init__ (line 36) | def __init__(self):
    method accepts (line 40) | def accepts(
    method convert (line 58) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_epub_converter.py
  class EpubConverter (line 26) | class EpubConverter(HtmlConverter):
    method __init__ (line 31) | def __init__(self):
    method accepts (line 35) | def accepts(
    method convert (line 53) | def convert(
    method _get_text_from_node (line 132) | def _get_text_from_node(self, dom: Document, tag_name: str) -> str | N...
    method _get_all_texts_from_nodes (line 140) | def _get_all_texts_from_nodes(self, dom: Document, tag_name: str) -> L...

FILE: packages/markitdown/src/markitdown/converters/_exiftool.py
  function _parse_version (line 7) | def _parse_version(version: str) -> tuple:
  function exiftool_metadata (line 11) | def exiftool_metadata(

FILE: packages/markitdown/src/markitdown/converters/_html_converter.py
  class HtmlConverter (line 20) | class HtmlConverter(DocumentConverter):
    method accepts (line 23) | def accepts(
    method convert (line 41) | def convert(
    method convert_string (line 73) | def convert_string(

FILE: packages/markitdown/src/markitdown/converters/_image_converter.py
  class ImageConverter (line 16) | class ImageConverter(DocumentConverter):
    method accepts (line 21) | def accepts(
    method convert (line 39) | def convert(
    method _get_llm_description (line 87) | def _get_llm_description(

FILE: packages/markitdown/src/markitdown/converters/_ipynb_converter.py
  class IpynbConverter (line 15) | class IpynbConverter(DocumentConverter):
    method accepts (line 18) | def accepts(
    method convert (line 46) | def convert(
    method _convert (line 57) | def _convert(self, notebook_content: dict) -> DocumentConverterResult:

FILE: packages/markitdown/src/markitdown/converters/_llm_caption.py
  function llm_caption (line 7) | def llm_caption(

FILE: packages/markitdown/src/markitdown/converters/_markdownify.py
  class _CustomMarkdownify (line 8) | class _CustomMarkdownify(markdownify.MarkdownConverter):
    method __init__ (line 18) | def __init__(self, **options: Any):
    method convert_hn (line 24) | def convert_hn(
    method convert_a (line 39) | def convert_a(
    method convert_img (line 85) | def convert_img(
    method convert_input (line 112) | def convert_input(
    method convert_soup (line 125) | def convert_soup(self, soup: Any) -> str:

FILE: packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py
  class OutlookMsgConverter (line 24) | class OutlookMsgConverter(DocumentConverter):
    method accepts (line 32) | def accepts(
    method convert (line 73) | def convert(
    method _get_stream_data (line 127) | def _get_stream_data(self, msg: Any, stream_path: str) -> Union[str, N...

FILE: packages/markitdown/src/markitdown/converters/_pdf_converter.py
  function _merge_partial_numbering_lines (line 14) | def _merge_partial_numbering_lines(text: str) -> str:
  function _to_markdown_table (line 78) | def _to_markdown_table(table: list[list[str]], include_separator: bool =...
  function _extract_form_content_from_words (line 120) | def _extract_form_content_from_words(page: Any) -> str | None:
  function _extract_tables_from_words (line 398) | def _extract_tables_from_words(page: Any) -> list[list[list[str]]]:
  class PdfConverter (line 495) | class PdfConverter(DocumentConverter):
    method accepts (line 502) | def accepts(
    method convert (line 520) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_plain_text_converter.py
  class PlainTextConverter (line 33) | class PlainTextConverter(DocumentConverter):
    method accepts (line 36) | def accepts(
    method convert (line 60) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_pptx_converter.py
  class PptxConverter (line 34) | class PptxConverter(DocumentConverter):
    method __init__ (line 39) | def __init__(self):
    method accepts (line 43) | def accepts(
    method convert (line 61) | def convert(
    method _is_picture (line 202) | def _is_picture(self, shape):
    method _is_table (line 210) | def _is_table(self, shape):
    method _convert_table_to_markdown (line 215) | def _convert_table_to_markdown(self, table, **kwargs):
    method _convert_chart_to_markdown (line 235) | def _convert_chart_to_markdown(self, chart):

FILE: packages/markitdown/src/markitdown/converters/_rss_converter.py
  class RssConverter (line 29) | class RssConverter(DocumentConverter):
    method __init__ (line 32) | def __init__(self):
    method accepts (line 36) | def accepts(
    method _check_xml (line 63) | def _check_xml(self, file_stream: BinaryIO) -> bool:
    method _feed_type (line 74) | def _feed_type(self, doc: Any) -> str | None:
    method convert (line 84) | def convert(
    method _parse_atom_type (line 101) | def _parse_atom_type(self, doc: Document) -> DocumentConverterResult:
    method _parse_rss_type (line 133) | def _parse_rss_type(self, doc: Document) -> DocumentConverterResult:
    method _parse_content (line 170) | def _parse_content(self, content: str) -> str:
    method _get_data_by_tag_name (line 179) | def _get_data_by_tag_name(

FILE: packages/markitdown/src/markitdown/converters/_transcribe_audio.py
  function transcribe_audio (line 23) | def transcribe_audio(file_stream: BinaryIO, *, audio_format: str = "wav"...

FILE: packages/markitdown/src/markitdown/converters/_wikipedia_converter.py
  class WikipediaConverter (line 20) | class WikipediaConverter(DocumentConverter):
    method accepts (line 23) | def accepts(
    method convert (line 51) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_xlsx_converter.py
  class XlsxConverter (line 36) | class XlsxConverter(DocumentConverter):
    method __init__ (line 41) | def __init__(self):
    method accepts (line 45) | def accepts(
    method convert (line 63) | def convert(
  class XlsConverter (line 98) | class XlsConverter(DocumentConverter):
    method __init__ (line 103) | def __init__(self):
    method accepts (line 107) | def accepts(
    method convert (line 125) | def convert(

FILE: packages/markitdown/src/markitdown/converters/_youtube_converter.py
  class YouTubeConverter (line 37) | class YouTubeConverter(DocumentConverter):
    method accepts (line 40) | def accepts(
    method convert (line 70) | def convert(
    method _get (line 199) | def _get(
    method _findKey (line 211) | def _findKey(self, json: Any, key: str) -> Union[str, None]:  # TODO: ...
    method _retry_operation (line 226) | def _retry_operation(self, operation, retries=3, delay=2):

FILE: packages/markitdown/src/markitdown/converters/_zip_converter.py
  class ZipConverter (line 22) | class ZipConverter(DocumentConverter):
    method __init__ (line 61) | def __init__(
    method accepts (line 69) | def accepts(
    method convert (line 87) | def convert(

FILE: packages/markitdown/tests/_test_vectors.py
  class FileTestVector (line 6) | class FileTestVector(object):

FILE: packages/markitdown/tests/test_cli_misc.py
  function test_version (line 9) | def test_version() -> None:
  function test_invalid_flag (line 18) | def test_invalid_flag() -> None:

FILE: packages/markitdown/tests/test_cli_vectors.py
  function shared_tmp_dir (line 39) | def shared_tmp_dir(tmp_path_factory):
  function test_output_to_stdout (line 44) | def test_output_to_stdout(shared_tmp_dir, test_vector) -> None:
  function test_output_to_file (line 66) | def test_output_to_file(shared_tmp_dir, test_vector) -> None:
  function test_input_from_stdin_without_hints (line 98) | def test_input_from_stdin_without_hints(shared_tmp_dir, test_vector) -> ...
  function test_convert_url (line 132) | def test_convert_url(shared_tmp_dir, test_vector):
  function test_output_to_file_with_data_uris (line 152) | def test_output_to_file_with_data_uris(shared_tmp_dir, test_vector) -> N...

FILE: packages/markitdown/tests/test_docintel_html.py
  function _make_converter (line 9) | def _make_converter(file_types):
  function test_docintel_accepts_html_extension (line 15) | def test_docintel_accepts_html_extension():
  function test_docintel_accepts_html_mimetype (line 21) | def test_docintel_accepts_html_mimetype():

FILE: packages/markitdown/tests/test_module_misc.py
  function validate_strings (line 100) | def validate_strings(result, expected_strings, exclude_strings=None):
  function test_stream_info_operations (line 110) | def test_stream_info_operations() -> None:
  function test_data_uris (line 182) | def test_data_uris() -> None:
  function test_file_uris (line 223) | def test_file_uris() -> None:
  function test_docx_comments (line 255) | def test_docx_comments() -> None:
  function test_docx_equations (line 264) | def test_docx_equations() -> None:
  function test_input_as_strings (line 277) | def test_input_as_strings() -> None:
  function test_doc_rlink (line 291) | def test_doc_rlink() -> None:
  function test_markitdown_remote (line 336) | def test_markitdown_remote() -> None:
  function test_speech_transcription (line 354) | def test_speech_transcription() -> None:
  function test_exceptions (line 370) | def test_exceptions() -> None:
  function test_markitdown_exiftool (line 389) | def test_markitdown_exiftool() -> None:
  function test_markitdown_llm_parameters (line 415) | def test_markitdown_llm_parameters() -> None:
  function test_markitdown_llm (line 463) | def test_markitdown_llm() -> None:

FILE: packages/markitdown/tests/test_module_vectors.py
  function test_guess_stream_info (line 28) | def test_guess_stream_info(test_vector):
  function test_convert_local (line 58) | def test_convert_local(test_vector):
  function test_convert_stream_with_hints (line 72) | def test_convert_stream_with_hints(test_vector):
  function test_convert_stream_without_hints (line 93) | def test_convert_stream_without_hints(test_vector):
  function test_convert_http_uri (line 110) | def test_convert_http_uri(test_vector):
  function test_convert_file_uri (line 127) | def test_convert_file_uri(test_vector):
  function test_convert_data_uri (line 142) | def test_convert_data_uri(test_vector):
  function test_convert_keep_data_uris (line 163) | def test_convert_keep_data_uris(test_vector):
  function test_convert_stream_keep_data_uris (line 181) | def test_convert_stream_keep_data_uris(test_vector):

FILE: packages/markitdown/tests/test_pdf_masterformat.py
  class TestMasterFormatPartialNumbering (line 14) | class TestMasterFormatPartialNumbering:
    method test_partial_numbering_pattern_regex (line 17) | def test_partial_numbering_pattern_regex(self):
    method test_masterformat_partial_numbering_not_split (line 34) | def test_masterformat_partial_numbering_not_split(self):
    method test_masterformat_content_preserved (line 73) | def test_masterformat_content_preserved(self):
    method test_merge_partial_numbering_with_empty_lines_between (line 115) | def test_merge_partial_numbering_with_empty_lines_between(self):
    method test_multiple_partial_numberings_all_merged (line 148) | def test_multiple_partial_numberings_all_merged(self):

FILE: packages/markitdown/tests/test_pdf_memory.py
  function _has_fpdf2 (line 24) | def _has_fpdf2() -> bool:
  function _make_form_page (line 33) | def _make_form_page():
  function _make_plain_page (line 52) | def _make_plain_page():
  function _mock_pdfplumber_open (line 70) | def _mock_pdfplumber_open(pages):
  class TestPdfMemoryOptimization (line 83) | class TestPdfMemoryOptimization:
    method test_page_close_called_on_every_page (line 86) | def test_page_close_called_on_every_page(self):
    method test_plain_text_pdf_falls_back_to_pdfminer (line 116) | def test_plain_text_pdf_falls_back_to_pdfminer(self):
    method test_plain_text_pdf_still_closes_all_pages (line 150) | def test_plain_text_pdf_still_closes_all_pages(self):
    method test_mixed_pdf_uses_form_extraction_per_page (line 177) | def test_mixed_pdf_uses_form_extraction_per_page(self):
    method test_only_one_pdfplumber_open_call (line 222) | def test_only_one_pdfplumber_open_call(self):
    method test_real_pdf_page_cleanup (line 249) | def test_real_pdf_page_cleanup(self):
  function _generate_table_pdf (line 271) | def _generate_table_pdf(num_pages: int) -> bytes:
  class TestPdfMemoryBenchmark (line 300) | class TestPdfMemoryBenchmark:
    method test_memory_does_not_grow_linearly (line 303) | def test_memory_does_not_grow_linearly(self):
    method test_memory_constant_across_page_counts (line 333) | def test_memory_constant_across_page_counts(self):

FILE: packages/markitdown/tests/test_pdf_tables.py
  function validate_strings (line 14) | def validate_strings(result, expected_strings, exclude_strings=None):
  function validate_markdown_table (line 24) | def validate_markdown_table(result, expected_headers, expected_data_samp...
  function extract_markdown_tables (line 40) | def extract_markdown_tables(text_content):
  function validate_table_structure (line 74) | def validate_table_structure(table):
  class TestPdfTableExtraction (line 97) | class TestPdfTableExtraction:
    method markitdown (line 101) | def markitdown(self):
    method test_borderless_table_extraction (line 105) | def test_borderless_table_extraction(self, markitdown):
    method test_borderless_table_no_duplication (line 273) | def test_borderless_table_no_duplication(self, markitdown):
    method test_borderless_table_correct_position (line 293) | def test_borderless_table_correct_position(self, markitdown):
    method test_receipt_pdf_extraction (line 337) | def test_receipt_pdf_extraction(self, markitdown):
    method test_multipage_invoice_extraction (line 495) | def test_multipage_invoice_extraction(self, markitdown):
    method test_academic_pdf_extraction (line 577) | def test_academic_pdf_extraction(self, markitdown):
    method test_scanned_pdf_handling (line 629) | def test_scanned_pdf_handling(self, markitdown):
    method test_movie_theater_booking_pdf_extraction (line 654) | def test_movie_theater_booking_pdf_extraction(self, markitdown):
  class TestPdfFullOutputComparison (line 722) | class TestPdfFullOutputComparison:
    method markitdown (line 726) | def markitdown(self):
    method test_movie_theater_full_output (line 730) | def test_movie_theater_full_output(self, markitdown):
    method test_sparse_borderless_table_full_output (line 779) | def test_sparse_borderless_table_full_output(self, markitdown):
    method test_repair_multipage_full_output (line 825) | def test_repair_multipage_full_output(self, markitdown):
    method test_receipt_full_output (line 867) | def test_receipt_full_output(self, markitdown):
    method test_academic_paper_full_output (line 910) | def test_academic_paper_full_output(self, markitdown):
    method test_medical_scan_full_output (line 951) | def test_medical_scan_full_output(self, markitdown):
  class TestPdfTableMarkdownFormat (line 981) | class TestPdfTableMarkdownFormat:
    method markitdown (line 985) | def markitdown(self):
    method test_markdown_table_has_pipe_format (line 989) | def test_markdown_table_has_pipe_format(self, markitdown):
    method test_markdown_table_columns_have_pipes (line 1013) | def test_markdown_table_columns_have_pipes(self, markitdown):
  class TestPdfTableStructureConsistency (line 1040) | class TestPdfTableStructureConsistency:
    method markitdown (line 1044) | def markitdown(self):
    method test_borderless_table_structure (line 1048) | def test_borderless_table_structure(self, markitdown):
    method test_multipage_invoice_table_structure (line 1068) | def test_multipage_invoice_table_structure(self, markitdown):
    method test_receipt_has_no_tables (line 1095) | def test_receipt_has_no_tables(self, markitdown):
    method test_scanned_pdf_no_tables (line 1115) | def test_scanned_pdf_no_tables(self, markitdown):
    method test_all_pdfs_table_rows_consistent (line 1136) | def test_all_pdfs_table_rows_consistent(self, markitdown):
    method test_borderless_table_data_integrity (line 1174) | def test_borderless_table_data_integrity(self, markitdown):