# $Id: __init__.py 7753 2014-06-24 14:52:59Z milde $ # Author: David Goodger # Maintainer: docutils-develop@lists.sourceforge.net # Copyright: This module has been placed in the public domain. """ Simple HyperText Markup Language document tree Writer. The output conforms to the XHTML version 1.0 Transitional DTD (*almost* strict). The output contains a minimum of formatting information. The cascading style sheet "html4css1.css" is required for proper viewing with a modern graphical browser. """ __docformat__ = 'reStructuredText' import sys import os import os.path import time import re import urllib try: # check for the Python Imaging Library import PIL.Image except ImportError: try: # sometimes PIL modules are put in PYTHONPATH's root import Image class PIL(object): pass # dummy wrapper PIL.Image = Image except ImportError: PIL = None import docutils from docutils import frontend, nodes, utils, writers, languages, io from docutils.utils.error_reporting import SafeString from docutils.transforms import writer_aux from docutils.utils.math import unichar2tex, pick_math_environment, math2html from docutils.utils.math.latex2mathml import parse_latex_math class Writer(writers.Writer): supported = ('html', 'html4css1', 'xhtml') """Formats this writer supports.""" default_stylesheet = 'html4css1.css' default_stylesheet_dirs = ['.', utils.relative_path( os.path.join(os.getcwd(), 'dummy'), os.path.dirname(__file__))] default_template = 'template.txt' default_template_path = utils.relative_path( os.path.join(os.getcwd(), 'dummy'), os.path.join(os.path.dirname(__file__), default_template)) settings_spec = ( 'HTML-Specific Options', None, (('Specify the template file (UTF-8 encoded). Default is "%s".' % default_template_path, ['--template'], {'default': default_template_path, 'metavar': ''}), ('Comma separated list of stylesheet URLs. ' 'Overrides previous --stylesheet and --stylesheet-path settings.', ['--stylesheet'], {'metavar': '', 'overrides': 'stylesheet_path', 'validator': frontend.validate_comma_separated_list}), ('Comma separated list of stylesheet paths. ' 'Relative paths are expanded if a matching file is found in ' 'the --stylesheet-dirs. With --link-stylesheet, ' 'the path is rewritten relative to the output HTML file. ' 'Default: "%s"' % default_stylesheet, ['--stylesheet-path'], {'metavar': '', 'overrides': 'stylesheet', 'validator': frontend.validate_comma_separated_list, 'default': [default_stylesheet]}), ('Embed the stylesheet(s) in the output HTML file. The stylesheet ' 'files must be accessible during processing. This is the default.', ['--embed-stylesheet'], {'default': 1, 'action': 'store_true', 'validator': frontend.validate_boolean}), ('Link to the stylesheet(s) in the output HTML file. ' 'Default: embed stylesheets.', ['--link-stylesheet'], {'dest': 'embed_stylesheet', 'action': 'store_false'}), ('Comma-separated list of directories where stylesheets are found. ' 'Used by --stylesheet-path when expanding relative path arguments. ' 'Default: "%s"' % default_stylesheet_dirs, ['--stylesheet-dirs'], {'metavar': '', 'validator': frontend.validate_comma_separated_list, 'default': default_stylesheet_dirs}), ('Specify the initial header level. Default is 1 for "

self.settings.option_limit): atts['colspan'] = 2 self.context.append('\n ') else: self.context.append('') self.body.append( self.starttag(node, 'td', CLASS='option-group', atts)) self.body.append('`') self.context.append(0) # count number of options def depart_option_group(self, node): self.context.pop() self.body.append('`\n') self.body.append(self.context.pop()) def visit_option_list(self, node): self.body.append( self.starttag(node, 'table', CLASS='docutils option-list', frame="void", rules="none")) self.body.append('\n' '\n' '\n') def depart_option_list(self, node): self.body.append('\n\n') def visit_option_list_item(self, node): self.body.append(self.starttag(node, 'tr', '')) def depart_option_list_item(self, node): self.body.append('\n') def visit_option_string(self, node): pass def depart_option_string(self, node): pass def visit_organization(self, node): self.visit_docinfo_item(node, 'organization') def depart_organization(self, node): self.depart_docinfo_item() def should_be_compact_paragraph(self, node): """ Determine if the
tags around paragraph ``node`` can be omitted. """ if (isinstance(node.parent, nodes.document) or isinstance(node.parent, nodes.compound)): # Never compact paragraphs in document or compound. return False for key, value in node.attlist(): if (node.is_not_default(key) and not (key == 'classes' and value in ([], ['first'], ['last'], ['first', 'last']))): # Attribute which needs to survive. return False first = isinstance(node.parent[0], nodes.label) # skip label for child in node.parent.children[first:]: # only first paragraph can be compact if isinstance(child, nodes.Invisible): continue if child is node: break return False parent_length = len([n for n in node.parent if not isinstance( n, (nodes.Invisible, nodes.label))]) if ( self.compact_simple or self.compact_field_list or self.compact_p and parent_length == 1): return True return False def visit_paragraph(self, node): if self.should_be_compact_paragraph(node): self.context.append('') else: self.body.append(self.starttag(node, 'p', '')) self.context.append('
\n') def depart_paragraph(self, node): self.body.append(self.context.pop()) def visit_problematic(self, node): if node.hasattr('refid'): self.body.append('' % node['refid']) self.context.append('') else: self.context.append('') self.body.append(self.starttag(node, 'span', '', CLASS='problematic')) def depart_problematic(self, node): self.body.append('') self.body.append(self.context.pop()) def visit_raw(self, node): if 'html' in node.get('format', '').split(): t = isinstance(node.parent, nodes.TextElement) and 'span' or 'div' if node['classes']: self.body.append(self.starttag(node, t, suffix='')) self.body.append(node.astext()) if node['classes']: self.body.append('' % t) # Keep non-HTML raw text out of output: raise nodes.SkipNode def visit_reference(self, node): atts = {'class': 'reference'} if 'refuri' in node: atts['href'] = node['refuri'] if ( self.settings.cloak_email_addresses and atts['href'].startswith('mailto:')): atts['href'] = self.cloak_mailto(atts['href']) self.in_mailto = True atts['class'] += ' external' else: assert 'refid' in node, \ 'References must have "refuri" or "refid" attribute.' atts['href'] = '#' + node['refid'] atts['class'] += ' internal' if not isinstance(node.parent, nodes.TextElement): assert len(node) == 1 and isinstance(node[0], nodes.image) atts['class'] += ' image-reference' self.body.append(self.starttag(node, 'a', '', **atts)) def depart_reference(self, node): self.body.append('') if not isinstance(node.parent, nodes.TextElement): self.body.append('\n') self.in_mailto = False def visit_revision(self, node): self.visit_docinfo_item(node, 'revision', meta=False) def depart_revision(self, node): self.depart_docinfo_item() def visit_row(self, node): self.body.append(self.starttag(node, 'tr', '')) node.column = 0 def depart_row(self, node): self.body.append('\n') def visit_rubric(self, node): self.body.append(self.starttag(node, 'p', '', CLASS='rubric')) def depart_rubric(self, node): self.body.append('
\n') def visit_section(self, node): self.section_level += 1 self.body.append( self.starttag(node, 'div', CLASS='section')) def depart_section(self, node): self.section_level -= 1 self.body.append('\n') def visit_sidebar(self, node): self.body.append( self.starttag(node, 'div', CLASS='sidebar')) self.set_first_last(node) self.in_sidebar = True def depart_sidebar(self, node): self.body.append('\n') self.in_sidebar = False def visit_status(self, node): self.visit_docinfo_item(node, 'status', meta=False) def depart_status(self, node): self.depart_docinfo_item() def visit_strong(self, node): self.body.append(self.starttag(node, 'strong', '')) def depart_strong(self, node): self.body.append('') def visit_subscript(self, node): self.body.append(self.starttag(node, 'sub', '')) def depart_subscript(self, node): self.body.append('') def visit_substitution_definition(self, node): """Internal only.""" raise nodes.SkipNode def visit_substitution_reference(self, node): self.unimplemented_visit(node) def visit_subtitle(self, node): if isinstance(node.parent, nodes.sidebar): self.body.append(self.starttag(node, 'p', '', CLASS='sidebar-subtitle')) self.context.append('
\n') elif isinstance(node.parent, nodes.document): self.body.append(self.starttag(node, 'h2', '', CLASS='subtitle')) self.context.append('

\n') self.in_document_title = len(self.body) elif isinstance(node.parent, nodes.section): tag = 'h%s' % (self.section_level + self.initial_header_level - 1) self.body.append( self.starttag(node, tag, '', CLASS='section-subtitle') + self.starttag({}, 'span', '', CLASS='section-subtitle')) self.context.append('\n' % tag) def depart_subtitle(self, node): self.body.append(self.context.pop()) if self.in_document_title: self.subtitle = self.body[self.in_document_title:-1] self.in_document_title = 0 self.body_pre_docinfo.extend(self.body) self.html_subtitle.extend(self.body) del self.body[:] def visit_superscript(self, node): self.body.append(self.starttag(node, 'sup', '')) def depart_superscript(self, node): self.body.append('') def visit_system_message(self, node): self.body.append(self.starttag(node, 'div', CLASS='system-message')) self.body.append('

') backref_text = '' if len(node['backrefs']): backrefs = node['backrefs'] if len(backrefs) == 1: backref_text = ('; backlink' % backrefs[0]) else: i = 1 backlinks = [] for backref in backrefs: backlinks.append('%s' % (backref, i)) i += 1 backref_text = ('; backlinks: %s' % ', '.join(backlinks)) if node.hasattr('line'): line = ', line %s' % node['line'] else: line = '' self.body.append('System Message: %s/%s ' '(%s%s)%s

\n' % (node['type'], node['level'], self.encode(node['source']), line, backref_text)) def depart_system_message(self, node): self.body.append('\n') def visit_table(self, node): self.context.append(self.compact_p) self.compact_p = True classes = ' '.join(['docutils', self.settings.table_style]).strip() self.body.append( self.starttag(node, 'table', CLASS=classes, border="1")) def depart_table(self, node): self.compact_p = self.context.pop() self.body.append('\n') def visit_target(self, node): if not ('refuri' in node or 'refid' in node or 'refname' in node): self.body.append(self.starttag(node, 'span', '', CLASS='target')) self.context.append('') else: self.context.append('') def depart_target(self, node): self.body.append(self.context.pop()) def visit_tbody(self, node): self.write_colspecs() self.body.append(self.context.pop()) # '\n' or '' self.body.append(self.starttag(node, 'tbody', valign='top')) def depart_tbody(self, node): self.body.append('\n') def visit_term(self, node): self.body.append(self.starttag(node, 'dt', '')) def depart_term(self, node): """ Leave the end tag to `self.visit_definition()`, in case there's a classifier. """ pass def visit_tgroup(self, node): # Mozilla needs : self.body.append(self.starttag(node, 'colgroup')) # Appended by thead or tbody: self.context.append('\n') node.stubs = [] def depart_tgroup(self, node): pass def visit_thead(self, node): self.write_colspecs() self.body.append(self.context.pop()) # '\n' # There may or may not be a ; this is for to use: self.context.append('') self.body.append(self.starttag(node, 'thead', valign='bottom')) def depart_thead(self, node): self.body.append('\n') def visit_title(self, node): """Only 6 section levels are supported by HTML.""" check_id = 0 # TODO: is this a bool (False) or a counter? close_tag = '

\n' if isinstance(node.parent, nodes.topic): self.body.append( self.starttag(node, 'p', '', CLASS='topic-title first')) elif isinstance(node.parent, nodes.sidebar): self.body.append( self.starttag(node, 'p', '', CLASS='sidebar-title')) elif isinstance(node.parent, nodes.Admonition): self.body.append( self.starttag(node, 'p', '', CLASS='admonition-title')) elif isinstance(node.parent, nodes.table): self.body.append( self.starttag(node, 'caption', '')) close_tag = '\n' elif isinstance(node.parent, nodes.document): self.body.append(self.starttag(node, 'h1', '', CLASS='title')) close_tag = '\n' self.in_document_title = len(self.body) else: assert isinstance(node.parent, nodes.section) h_level = self.section_level + self.initial_header_level - 1 atts = {} if (len(node.parent) >= 2 and isinstance(node.parent[1], nodes.subtitle)): atts['CLASS'] = 'with-subtitle' self.body.append( self.starttag(node, 'h%s' % h_level, '', **atts)) atts = {} if node.hasattr('refid'): atts['class'] = 'toc-backref' atts['href'] = '#' + node['refid'] if atts: self.body.append(self.starttag({}, 'a', '', **atts)) close_tag = '\n' % (h_level) else: close_tag = '\n' % (h_level) self.context.append(close_tag) def depart_title(self, node): self.body.append(self.context.pop()) if self.in_document_title: self.title = self.body[self.in_document_title:-1] self.in_document_title = 0 self.body_pre_docinfo.extend(self.body) self.html_title.extend(self.body) del self.body[:] def visit_title_reference(self, node): self.body.append(self.starttag(node, 'cite', '')) def depart_title_reference(self, node): self.body.append('') def visit_topic(self, node): self.body.append(self.starttag(node, 'div', CLASS='topic')) self.topic_classes = node['classes'] def depart_topic(self, node): self.body.append('\n') self.topic_classes = [] def visit_transition(self, node): self.body.append(self.emptytag(node, 'hr', CLASS='docutils')) def depart_transition(self, node): pass def visit_version(self, node): self.visit_docinfo_item(node, 'version', meta=False) def depart_version(self, node): self.depart_docinfo_item() def unimplemented_visit(self, node): raise NotImplementedError('visiting unimplemented node type: %s' % node.__class__.__name__) class SimpleListChecker(nodes.GenericNodeVisitor): """ Raise `nodes.NodeFound` if non-simple list item is encountered. Here "simple" means a list item containing nothing other than a single paragraph, a simple list, or a paragraph followed by a simple list. """ def default_visit(self, node): raise nodes.NodeFound def visit_bullet_list(self, node): pass def visit_enumerated_list(self, node): pass def visit_list_item(self, node): children = [] for child in node.children: if not isinstance(child, nodes.Invisible): children.append(child) if (children and isinstance(children[0], nodes.paragraph) and (isinstance(children[-1], nodes.bullet_list) or isinstance(children[-1], nodes.enumerated_list))): children.pop() if len(children) <= 1: return else: raise nodes.NodeFound def visit_paragraph(self, node): raise nodes.SkipNode def invisible_visit(self, node): """Invisible nodes should be ignored.""" raise nodes.SkipNode visit_comment = invisible_visit visit_substitution_definition = invisible_visit visit_target = invisible_visit visit_pending = invisible_visit