# -*- coding: utf-8 -*- from docutils import core from docutils import nodes from docutils.parsers.rst import Directive from docutils.parsers.rst import directives from pygments import highlight from pygments.formatters import HtmlFormatter from pygments.lexers import TextLexer from pygments.lexers import get_lexer_by_name class Pygments(Directive): """ Source code syntax hightlighting for ReST syntax.""" required_arguments = 1 optional_arguments = 0 final_argument_whitespace = True option_spec = { 'linenos': directives.flag, 'emphasize-lines': directives.unchanged_required, } has_content = True def run(self): self.assert_has_content() try: lexer = get_lexer_by_name(self.arguments[0]) except ValueError: # no lexer found - use the text one instead of an exception lexer = TextLexer() args = {'noclasses': False} if 'linenos' in self.options: args['linenos'] = 'table' if 'emphasize-lines' in self.options: args['hl_lines'] = self.options['emphasize-lines'].split(',') formatter = HtmlFormatter(**args) parsed = highlight(u'\n'.join(self.content), lexer, formatter) return [nodes.raw('', parsed, format='html')] directives.register_directive('sourcecode', Pygments) directives.register_directive('code-block', Pygments) def html_parts(input_string, source_path=None, destination_path=None, input_encoding='unicode', doctitle=1, initial_header_level=1): """ Given an input string, returns a dictionary of HTML document parts. Dictionary keys are the names of parts, and values are Unicode strings; encoding is up to the client. Parameters: - `input_string`: A multi-line text string; required. - `source_path`: Path to the source file or object. Optional, but useful for diagnostic output (system messages). - `destination_path`: Path to the file or object which will receive the output; optional. Used for determining relative paths (stylesheets, source links, etc.). - `input_encoding`: The encoding of `input_string`. If it is an encoded 8-bit string, provide the correct encoding. If it is a Unicode string, use "unicode", the default. - `doctitle`: Disable the promotion of a lone top-level section title to document title (and subsequent section title to document subtitle promotion); enabled by default. - `initial_header_level`: The initial level for header elements (e.g. 1 for "

"). """ overrides = { 'input_encoding': input_encoding, 'doctitle_xform': doctitle, 'initial_header_level': initial_header_level, 'report_level': 5 } parts = core.publish_parts( source=input_string, source_path=source_path, destination_path=destination_path, writer_name='html', settings_overrides=overrides) return parts def html_body(input_string, source_path=None, destination_path=None, input_encoding='unicode', doctitle=1, initial_header_level=1): """ Given an input string, returns an HTML fragment as a string. The return value is the contents of the element. Parameters (see `html_parts()` for the remainder): - `output_encoding`: The desired encoding of the output. If a Unicode string is desired, use the default value of "unicode" . """ parts = html_parts( input_string=input_string, source_path=source_path, destination_path=destination_path, input_encoding=input_encoding, doctitle=doctitle, initial_header_level=initial_header_level) fragment = parts['html_body'] return fragment