# $Id$ # -*- coding: utf-8 -*- # Authors: David Goodger ; Ueli Schlaepfer; Günter Milde # Maintainer: docutils-develop@lists.sourceforge.net # Copyright: This module has been placed in the public domain. """ Transforms needed by most or all documents: - `Decorations`: Generate a document's header & footer. - `Messages`: Placement of system messages stored in `nodes.document.transform_messages`. - `TestMessages`: Like `Messages`, used on test runs. - `FinalReferences`: Resolve remaining references. """ __docformat__ = 'reStructuredText' import re import sys import time from docutils import nodes, utils from docutils.transforms import TransformError, Transform from docutils.utils import smartquotes class Decorations(Transform): """ Populate a document's decoration element (header, footer). """ default_priority = 820 def apply(self): header_nodes = self.generate_header() if header_nodes: decoration = self.document.get_decoration() header = decoration.get_header() header.extend(header_nodes) footer_nodes = self.generate_footer() if footer_nodes: decoration = self.document.get_decoration() footer = decoration.get_footer() footer.extend(footer_nodes) def generate_header(self): return None def generate_footer(self): # @@@ Text is hard-coded for now. # Should be made dynamic (language-dependent). settings = self.document.settings if settings.generator or settings.datestamp or settings.source_link \ or settings.source_url: text = [] if settings.source_link and settings._source \ or settings.source_url: if settings.source_url: source = settings.source_url else: source = utils.relative_path(settings._destination, settings._source) text.extend([ nodes.reference('', 'View document source', refuri=source), nodes.Text('.\n')]) if settings.datestamp: datestamp = time.strftime(settings.datestamp, time.gmtime()) text.append(nodes.Text('Generated on: ' + datestamp + '.\n')) if settings.generator: text.extend([ nodes.Text('Generated by '), nodes.reference('', 'Docutils', refuri= 'http://docutils.sourceforge.net/'), nodes.Text(' from '), nodes.reference('', 'reStructuredText', refuri='http://' 'docutils.sourceforge.net/rst.html'), nodes.Text(' source.\n')]) return [nodes.paragraph('', '', *text)] else: return None class ExposeInternals(Transform): """ Expose internal attributes if ``expose_internals`` setting is set. """ default_priority = 840 def not_Text(self, node): return not isinstance(node, nodes.Text) def apply(self): if self.document.settings.expose_internals: for node in self.document.traverse(self.not_Text): for att in self.document.settings.expose_internals: value = getattr(node, att, None) if value is not None: node['internal:' + att] = value class Messages(Transform): """ Place any system messages generated after parsing into a dedicated section of the document. """ default_priority = 860 def apply(self): unfiltered = self.document.transform_messages threshold = self.document.reporter.report_level messages = [] for msg in unfiltered: if msg['level'] >= threshold and not msg.parent: messages.append(msg) if messages: section = nodes.section(classes=['system-messages']) # @@@ get this from the language module? section += nodes.title('', 'Docutils System Messages') section += messages self.document.transform_messages[:] = [] self.document += section class FilterMessages(Transform): """ Remove system messages below verbosity threshold. """ default_priority = 870 def apply(self): for node in self.document.traverse(nodes.system_message): if node['level'] < self.document.reporter.report_level: node.parent.remove(node) class TestMessages(Transform): """ Append all post-parse system messages to the end of the document. Used for testing purposes. """ default_priority = 880 def apply(self): for msg in self.document.transform_messages: if not msg.parent: self.document += msg class StripComments(Transform): """ Remove comment elements from the document tree (only if the ``strip_comments`` setting is enabled). """ default_priority = 740 def apply(self): if self.document.settings.strip_comments: for node in self.document.traverse(nodes.comment): node.parent.remove(node) class StripClassesAndElements(Transform): """ Remove from the document tree all elements with classes in `self.document.settings.strip_elements_with_classes` and all "classes" attribute values in `self.document.settings.strip_classes`. """ default_priority = 420 def apply(self): if not (self.document.settings.strip_elements_with_classes or self.document.settings.strip_classes): return # prepare dicts for lookup (not sets, for Python 2.2 compatibility): self.strip_elements = dict( [(key, None) for key in (self.document.settings.strip_elements_with_classes or [])]) self.strip_classes = dict( [(key, None) for key in (self.document.settings.strip_classes or [])]) for node in self.document.traverse(self.check_classes): node.parent.remove(node) def check_classes(self, node): if isinstance(node, nodes.Element): for class_value in node['classes'][:]: if class_value in self.strip_classes: node['classes'].remove(class_value) if class_value in self.strip_elements: return 1 class SmartQuotes(Transform): """ Replace ASCII quotation marks with typographic form. Also replace multiple dashes with em-dash/en-dash characters. """ default_priority = 850 def __init__(self, document, startnode): Transform.__init__(self, document, startnode=startnode) self.unsupported_languages = set() def get_tokens(self, txtnodes): # A generator that yields ``(texttype, nodetext)`` tuples for a list # of "Text" nodes (interface to ``smartquotes.educate_tokens()``). texttype = {True: 'literal', # "literal" text is not changed: False: 'plain'} for txtnode in txtnodes: nodetype = texttype[isinstance(txtnode.parent, (nodes.literal, nodes.math, nodes.image, nodes.raw, nodes.problematic))] yield (nodetype, txtnode.astext()) def apply(self): smart_quotes = self.document.settings.smart_quotes if not smart_quotes: return try: alternative = smart_quotes.startswith('alt') except AttributeError: alternative = False # print repr(alternative) document_language = self.document.settings.language_code # "Educate" quotes in normal text. Handle each block of text # (TextElement node) as a unit to keep context around inline nodes: for node in self.document.traverse(nodes.TextElement): # skip preformatted text blocks and special elements: if isinstance(node, (nodes.FixedTextElement, nodes.Special)): continue # nested TextElements are not "block-level" elements: if isinstance(node.parent, nodes.TextElement): continue # list of text nodes in the "text block": txtnodes = [txtnode for txtnode in node.traverse(nodes.Text) if not isinstance(txtnode.parent, nodes.option_string)] # language: use typographical quotes for language "lang" lang = node.get_language_code(document_language) # use alternative form if `smart-quotes` setting starts with "alt": if alternative: if '-x-altquot' in lang: lang = lang.replace('-x-altquot', '') else: lang += '-x-altquot' # drop subtags missing in quotes: for tag in utils.normalize_language_tag(lang): if tag in smartquotes.smartchars.quotes: lang = tag break else: # language not supported: (keep ASCII quotes) if lang not in self.unsupported_languages: self.document.reporter.warning('No smart quotes ' 'defined for language "%s".'%lang, base_node=node) self.unsupported_languages.add(lang) lang = '' # Iterator educating quotes in plain text: # '2': set all, using old school en- and em- dash shortcuts teacher = smartquotes.educate_tokens(self.get_tokens(txtnodes), attr='2', language=lang) for txtnode, newtext in zip(txtnodes, teacher): txtnode.parent.replace(txtnode, nodes.Text(newtext)) self.unsupported_languages = set() # reset