def convert_run(self, run):
ans = SPAN()
self.object_map[ans] = run
text = Text(ans, 'text', [])
for child in run:
if self.namespace.is_tag(child, 'w:t'):
if not child.text:
continue
space = child.get(XML('space'), None)
preserve = False
ctext = child.text
if space != 'preserve':
# Remove leading and trailing whitespace. Word ignores
# leading and trailing whitespace without preserve
ctext = ctext.strip(' \n\r\t')
# Only use a <span> with white-space:pre-wrap if this element
# actually needs it, i.e. if it has more than one
# consecutive space or it has newlines or tabs.
multi_spaces = self.ms_pat.search(ctext) is not None
preserve = multi_spaces or self.ws_pat.search(ctext) is not None
if preserve:
text.add_elem(SPAN(ctext, style="white-space:pre-wrap"))
ans.append(text.elem)
else:
text.buf.append(ctext)
elif self.namespace.is_tag(child, 'w:cr'):
text.add_elem(BR())
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:br'):
typ = self.namespace.get(child, 'w:type')
if typ in {'column', 'page'}:
br = BR(style='page-break-after:always')
else:
clear = child.get('clear', None)
if clear in {'all', 'left', 'right'}:
br = BR(style='clear:%s'%('both' if clear == 'all' else clear))
else:
br = BR()
text.add_elem(br)
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:drawing') or self.namespace.is_tag(child, 'w:pict'):
for img in self.images.to_html(child, self.current_page, self.docx, self.dest_dir):
text.add_elem(img)
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:footnoteReference') or self.namespace.is_tag(child, 'w:endnoteReference'):
anchor, name = self.footnotes.get_ref(child)
if anchor and name:
l = A(SUP(name, id='back_%s' % anchor), href='#' + anchor, title=name)
l.set('class', 'noteref')
text.add_elem(l)
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:tab'):
spaces = int(math.ceil((self.settings.default_tab_stop / 36) * 6))
text.add_elem(SPAN(NBSP * spaces))
ans.append(text.elem)
ans[-1].set('class', 'tab')
elif self.namespace.is_tag(child, 'w:noBreakHyphen'):
text.buf.append('\u2011')
elif self.namespace.is_tag(child, 'w:softHyphen'):
text.buf.append('\u00ad')
if text.buf:
setattr(text.elem, text.attr, ''.join(text.buf))
style = self.styles.resolve_run(run)
if style.vert_align in {'superscript', 'subscript'}:
ans.tag = 'sub' if style.vert_align == 'subscript' else 'sup'
if style.lang is not inherit:
lang = html_lang(style.lang)
if lang is not None and lang != self.doc_lang:
ans.set('lang', lang)
if style.rtl is True:
ans.set('dir', 'rtl')
if is_symbol_font(style.font_family):
for elem in text:
if elem.text:
elem.text = map_symbol_text(elem.text, style.font_family)
if elem.tail:
elem.tail = map_symbol_text(elem.tail, style.font_family)
style.font_family = 'sans-serif'
return ans
def convert_run(self, run):
ans = SPAN()
self.object_map[ans] = run
text = Text(ans, 'text', [])
for child in run:
if self.namespace.is_tag(child, 'w:t'):
if not child.text:
continue
space = child.get(XML('space'), None)
preserve = False
ctext = child.text
if space != 'preserve':
# Remove leading and trailing whitespace. Word ignores
# leading and trailing whitespace without preserve
ctext = ctext.strip(' \n\r\t')
# Only use a <span> with white-space:pre-wrap if this element
# actually needs it, i.e. if it has more than one
# consecutive space or it has newlines or tabs.
multi_spaces = self.ms_pat.search(ctext) is not None
preserve = multi_spaces or self.ws_pat.search(ctext) is not None
if preserve:
text.add_elem(SPAN(ctext, style="white-space:pre-wrap"))
ans.append(text.elem)
else:
text.buf.append(ctext)
elif self.namespace.is_tag(child, 'w:cr'):
text.add_elem(BR())
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:br'):
typ = self.namespace.get(child, 'w:type')
if typ in {'column', 'page'}:
br = BR(style='page-break-after:always')
else:
clear = child.get('clear', None)
if clear in {'all', 'left', 'right'}:
br = BR(style='clear:%s'%('both' if clear == 'all' else clear))
else:
br = BR()
text.add_elem(br)
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:drawing') or self.namespace.is_tag(child, 'w:pict'):
for img in self.images.to_html(child, self.current_page, self.docx, self.dest_dir):
text.add_elem(img)
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:footnoteReference') or self.namespace.is_tag(child, 'w:endnoteReference'):
anchor, name = self.footnotes.get_ref(child)
if anchor and name:
l = A(SUP(name, id='back_%s' % anchor), href='#' + anchor, title=name)
l.set('class', 'noteref')
text.add_elem(l)
ans.append(text.elem)
elif self.namespace.is_tag(child, 'w:tab'):
spaces = int(math.ceil((self.settings.default_tab_stop / 36) * 6))
text.add_elem(SPAN(NBSP * spaces))
ans.append(text.elem)
ans[-1].set('class', 'tab')
elif self.namespace.is_tag(child, 'w:noBreakHyphen'):
text.buf.append(u'\u2011')
elif self.namespace.is_tag(child, 'w:softHyphen'):
text.buf.append(u'\u00ad')
if text.buf:
setattr(text.elem, text.attr, ''.join(text.buf))
style = self.styles.resolve_run(run)
if style.vert_align in {'superscript', 'subscript'}:
ans.tag = 'sub' if style.vert_align == 'subscript' else 'sup'
if style.lang is not inherit:
lang = html_lang(style.lang)
if lang is not None and lang != self.doc_lang:
ans.set('lang', lang)
if style.rtl is True:
ans.set('dir', 'rtl')
if is_symbol_font(style.font_family):
for elem in text:
if elem.text:
elem.text = map_symbol_text(elem.text, style.font_family)
if elem.tail:
elem.tail = map_symbol_text(elem.tail, style.font_family)
style.font_family = 'sans-serif'
return ans