U \>eWS@sddlmZddlZddlZddlZddlZddlmZmZm Z m Z m Z m Z m Z ddlmZddlmZddlmZddlmZdd lmZdd lmZdd lmZdd lmZmZdd lmZerddl m!Z!dddgZ"e#dZ$GdddZ%ddddddZ&ddddZ'dS)) annotationsN) TYPE_CHECKINGAnyBinaryIOCallableClassVarMappingSequence)util)build_preprocessors)build_block_parser)build_treeprocessors)build_inlinepatterns)build_postprocessors) Extension)to_html_stringto_xhtml_string)BLOCK_LEVEL_ELEMENTS)ElementMarkdownmarkdownmarkdownFromFileZMARKDOWNc@seZdZUdZdZeedZded<ddZ ddd d Z d d dd ddZ ddddddZ dddddZ ddddZdddddZddd d!d"Zddd#d$d%Zd,d'd'd(dd)d*d+Zd&S)-ra A parser which converts Markdown to HTML. Attributes: Markdown.tab_length (int): The number of spaces which correspond to a single tab. Default: `4`. Markdown.ESCAPED_CHARS (list[str]): List of characters which get the backslash escape treatment. Markdown.block_level_elements (list[str]): List of HTML tags which get treated as block-level elements. See [`markdown.util.BLOCK_LEVEL_ELEMENTS`][] for the full list of elements. Markdown.registeredExtensions (list[Extension]): List of extensions which have called [`registerExtension`][markdown.Markdown.registerExtension] during setup. Markdown.doc_tag (str): Element used to wrap document. Default: `div`. Markdown.stripTopLevelTags (bool): Indicates whether the `doc_tag` should be removed. Default: 'True'. Markdown.references (dict[str, tuple[str, str]]): A mapping of link references found in a parsed document where the key is the reference name and the value is a tuple of the URL and title. Markdown.htmlStash (util.HtmlStash): The instance of the `HtmlStash` used by an instance of this class. Markdown.output_formats (dict[str, Callable[xml.etree.ElementTree.Element]]): A mapping of known output formats by name and their respective serializers. Each serializer must be a callable which accepts an [`Element`][xml.etree.ElementTree.Element] and returns a `str`. Markdown.output_format (str): The output format set by [`set_output_format`][markdown.Markdown.set_output_format]. Markdown.serializer (Callable[xml.etree.ElementTree.Element]): The serializer set by [`set_output_format`][markdown.Markdown.set_output_format]. Markdown.preprocessors (util.Registry): A collection of [`preprocessors`][markdown.preprocessors]. Markdown.parser (blockparser.BlockParser): A collection of [`blockprocessors`][markdown.blockprocessors]. Markdown.inlinePatterns (util.Registry): A collection of [`inlinepatterns`][markdown.inlinepatterns]. Markdown.treeprocessors (util.Registry): A collection of [`treeprocessors`][markdown.treeprocessors]. Markdown.postprocessors (util.Registry): A collection of [`postprocessors`][markdown.postprocessors]. div)htmlxhtmlz-ClassVar[dict[str, Callable[[Element], str]]]output_formatscKs|dd|_ddddddd d d d d dddddg|_t|_g|_d|_d|_| i|_ t |_ |j|dg|did||dd|dS)a Creates a new Markdown instance. Keyword Arguments: extensions (list[Extension | str]): A list of extensions. If an item is an instance of a subclass of [`markdown.extensions.Extension`][], the instance will be used as-is. If an item is of type `str`, it is passed to [`build_extension`][markdown.Markdown.build_extension] with its corresponding `extension_configs` and the returned instance of [`markdown.extensions.Extension`][] is used. extension_configs (dict[str, dict[str, Any]]): Configuration settings for extensions. output_format (str): Format of output. Supported formats are: * `xhtml`: Outputs XHTML style tags. Default. * `html`: Outputs HTML style tags. tab_length (int): Length of tabs in the source. Default: `4` tab_length\`*_{}[]()>#+-.!T extensionsZextension_configs)r0configs output_formatrN)getrZ ESCAPED_CHARSrcopyblock_level_elementsregisteredExtensionsZdocTypestripTopLevelTags build_parser referencesr Z HtmlStash htmlStashregisterExtensionsset_output_formatreset)selfkwargsr@1/tmp/pip-unpacked-wheel-wj0og6ym/markdown/core.py__init__Xs<   zMarkdown.__init__)returncCs6t||_t||_t||_t||_t||_ |S)a0 Build the parser from the various parts. Assigns a value to each of the following attributes on the class instance: * **`Markdown.preprocessors`** ([`Registry`][markdown.util.Registry]) -- A collection of [`preprocessors`][markdown.preprocessors]. * **`Markdown.parser`** ([`BlockParser`][markdown.blockparser.BlockParser]) -- A collection of [`blockprocessors`][markdown.blockprocessors]. * **`Markdown.inlinePatterns`** ([`Registry`][markdown.util.Registry]) -- A collection of [`inlinepatterns`][markdown.inlinepatterns]. * **`Markdown.treeprocessors`** ([`Registry`][markdown.util.Registry]) -- A collection of [`treeprocessors`][markdown.treeprocessors]. * **`Markdown.postprocessors`** ([`Registry`][markdown.util.Registry]) -- A collection of [`postprocessors`][markdown.postprocessors]. This method could be redefined in a subclass to build a custom parser which is made up of a different combination of processors and patterns. ) r preprocessorsr parserrZinlinePatternsrtreeprocessorsrpostprocessors)r>r@r@rAr8s      zMarkdown.build_parserzSequence[Extension | str]zMapping[str, dict[str, Any]])r0r1rCcCs|D]z}t|tr&||||i}t|trV||td|jj |jj fq|dk rt d |jj |jj tj tj q|S)a Load a list of extensions into an instance of the `Markdown` class. Arguments: extensions (list[Extension | str]): A list of extensions. If an item is an instance of a subclass of [`markdown.extensions.Extension`][], the instance will be used as-is. If an item is of type `str`, it is passed to [`build_extension`][markdown.Markdown.build_extension] with its corresponding `configs` and the returned instance of [`markdown.extensions.Extension`][] is used. configs (dict[str, dict[str, Any]]): Configuration settings for extensions. z&Successfully loaded extension "%s.%s".Nz*Extension "{}.{}" must be of type: "{}.{}") isinstancestrbuild_extensionr3rZextendMarkdownloggerdebug __class__ __module____name__ TypeErrorformat)r>r0r1extr@r@rAr;s(   zMarkdown.registerExtensionsrIzMapping[str, Any]r)ext_namer1rCc s2t|}fddtD}|r8|d}|f|SdkrLddndf\}zt}tdWnBt k r}z$d}|f|j dd |_ W5d }~XYnX|rt ||f|Sz|j f|WSt k r,}z2|j d}d |f}|f|j dd |_ W5d }~XYnXd S) a Build extension from a string name, then return an instance using the given `configs`. Arguments: ext_name: Name of extension as a string. configs: Configuration settings for extension. Returns: An instance of the extension with the given configuration settings. First attempt to load an entry point. The string name must be registered as an entry point in the `markdown.extensions` group which points to a subclass of the [`markdown.extensions.Extension`][] class. If multiple distributions have registered the same name, the first one found is returned. If no entry point is found, assume dot notation (`path.to.module:ClassName`). Load the specified class and return an instance. If no class is specified, import the module and call a `makeExtension` function and return the [`markdown.extensions.Extension`][] instance returned by that function. csg|]}|jkr|qSr@)name).0eprSr@rA s z,Markdown.build_extension..r:r r/z,Successfully imported extension module "%s".zFailed loading extension "%s".Nz%Failed to initiate extension '%s': %s)dictr Zget_installed_extensionsloadsplit importlib import_modulerKrL ImportErrorargsgetattrZ makeExtensionAttributeError) r>rSr1 entry_pointsrR class_namemoduleemessager@rWrArJs4     zMarkdown.build_extension) extensionrCcCs|j||S)a Register an extension as having a resettable state. Arguments: extension: An instance of the extension to register. This should get called once by an extension during setup. A "registered" extension's `reset` method is called by [`Markdown.reset()`][markdown.Markdown.reset]. Not all extensions have or need a resettable state, and so it should not be assumed that all extensions are "registered." )r6appendr>rhr@r@rAregisterExtensions zMarkdown.registerExtensioncCs6|j|j|jD]}t|dr|q|S)z Resets all state variables to prepare the parser instance for new input. Called once upon creation of a class instance. Should be called manually between calls to [`Markdown.convert`][markdown.Markdown.convert]. r=)r:r=r9clearr6hasattrrjr@r@rAr=s      zMarkdown.reset)rQrCc Cs|d|_z|j|j|_Wnltk r}zNt|j}|d|jdd |df}|f|j dd|_ W5d}~XYnX|S)z Set the output format for the class instance. Arguments: format: Must be a known value in `Markdown.output_formats`. Z145z+Invalid Output Format: "%s". Use one of %s."z", "r N) lowerrstripr2r serializerKeyErrorlistkeyssortjoinr`)r>rQrfZ valid_formatsrgr@r@rAr<szMarkdown.set_output_formatrbool)tagrCcCs"t|tr|d|jkSdS)z Check if the given `tag` is a block level HTML tag. Returns `True` for any string listed in `Markdown.block_level_elements`. A `tag` which is not a string always returns `False`. /F)rHrIrorpr5)r>rxr@r@rAis_block_level.s zMarkdown.is_block_level)sourcerCc Csn|s dSz t|}Wn2tk rJ}z|jd7_W5d}~XYnX|d|_|jD]}||j|_q^|j |j }|j D]}||}|dk r|}q| |}|j rNzB|d|jt|jd}|d|j} ||| }WnRtk rL}z2|d|jr*d}ntd ||W5d}~XYnX|jD]} | |}qT|S) a Convert a Markdown string to a string in the specified output format. Arguments: source: Markdown formatted text as Unicode or ASCII string. Returns: A string in the specified output format. Markdown parsing takes place in five steps: 1. A bunch of [`preprocessors`][markdown.preprocessors] munge the input text. 2. A [`BlockParser`][markdown.blockparser.BlockParser] parses the high-level structural elements of the pre-processed text into an [`ElementTree`][xml.etree.ElementTree.ElementTree] object. 3. A bunch of [`treeprocessors`][markdown.treeprocessors] are run against the [`ElementTree`][xml.etree.ElementTree.ElementTree] object. One such `treeprocessor` ([`markdown.treeprocessors.InlineProcessor`][]) runs [`inlinepatterns`][markdown.inlinepatterns] against the [`ElementTree`][xml.etree.ElementTree.ElementTree] object, parsing inline markup. 4. Some [`postprocessors`][markdown.postprocessors] are run against the text after the [`ElementTree`][xml.etree.ElementTree.ElementTree] object has been serialized into text. 5. The output is returned as a string. r/z/. -- Note: Markdown only accepts Unicode input!N z<%s>zz<%s />z4Markdown failed to strip top-level tags. Document=%r)striprIUnicodeDecodeErrorreasonr\linesrDrunrEZ parseDocumentgetrootrFrqr7indexdoc_taglenrindex ValueErrorendswithrG) r>r{rfpreprootZ treeprocessorZnewRootoutputstartendppr@r@rAconvert;sL       zMarkdown.convertNzstr | BinaryIO | Nonez str | None)inputrencodingrCc Cs|pd}|rHt|tr(tj|d|d}nt||}|}|n tj}| d}| |}|rt|trtj|d|dd}| ||qt |}||dd}| |n| |d}tjj ||S) a Converts a Markdown file and returns the HTML as a Unicode string. Decodes the file using the provided encoding (defaults to `utf-8`), passes the file content to markdown, and outputs the HTML to either the provided stream or the file with provided name, using the same encoding as the source file. The [`xmlcharrefreplace`](https://docs.python.org/3/library/codecs.html#error-handlers) error handler is used when encoding the output. **Note:** This is the only place that decoding and encoding of Unicode takes place in Python-Markdown. (All other code is Unicode-in / Unicode-out.) Arguments: input: File object or path. Reads from `stdin` if `None`. output: File object or path. Writes to `stdout` if `None`. encoding: Encoding of input and output files. Defaults to `utf-8`. zutf-8r)moderuwxmlcharrefreplace)rerrors)r)rHrIcodecsopen getreaderreadclosesysstdinlstriprwrite getwriterencodestdoutbuffer) r>rrrZ input_filetextrZ output_filewriterr@r@rA convertFiles0            zMarkdown.convertFile)NNN)rOrN __qualname____doc__rrrr__annotations__rBr8r;rJrkr=r<rzrrr@r@r@rAr.s$  +$5 KrIr)rr?rCcKstf|}||S)a5 Convert a markdown string to HTML and return HTML as a Unicode string. This is a shortcut function for [`Markdown`][markdown.Markdown] class to cover the most basic use case. It initializes an instance of [`Markdown`][markdown.Markdown], loads the necessary extensions and runs the parser on the given text. Arguments: text: Markdown formatted text as Unicode or ASCII string. Keyword arguments: **kwargs: Any arguments accepted by the Markdown class. Returns: A string in the specified output format. )rr)rr?mdr@r@rArs )r?cKs4tf|}||dd|dd|dddS)aE Read Markdown text from a file and write output to a file or a stream. This is a shortcut function which initializes an instance of [`Markdown`][markdown.Markdown], and calls the [`convertFile`][markdown.Markdown.convertFile] method rather than [`convert`][markdown.Markdown.convert]. Keyword arguments: input (str | BinaryIO): A file name or readable object. output (str | BinaryIO): A file name or writable object. encoding (str): Encoding of input and output. **kwargs: Any arguments accepted by the `Markdown` class. rNrr)rrr3)r?rr@r@rArs    )( __future__rrrloggingr]typingrrrrrrr r/r rDr Zblockprocessorsr rFrZinlinepatternsrrGrr0rZ serializersrrrxml.etree.ElementTreer__all__ getLoggerrKrrrr@r@r@rAs0 $           $