def __init__(self, element):
if type(element) in (str, unicode):
tree = ET.fromstring('<html_example>' + element + "</html_example>")
self.el = tree
else:
self.el = element
from ist.utils.texlist2 import TexList
self.tex = TexList()
def href_id(self):
if self.parent:
parent_id = str(self.parent.href_id)
if FormatMode.format_mode == FormatMode.LATEX_MODE:
if parent_id.startswith('IT::'):
return '{}::{}'.format(parent_id[4:], TexList.name_mode(self.name))
return '{}::{}'.format(parent_id, TexList.name_mode(self.name))
return '{self.parent.href_id}-{self.name}'.format(self=self)
return self.name
def href_id(self):
if self.parent:
parent_id = str(self.parent.href_id)
if FormatMode.format_mode == FormatMode.LATEX_MODE:
if parent_id.startswith('IT::'):
return '{}::{}'.format(parent_id[4:],
TexList.name_mode(self.name))
return '{}::{}'.format(parent_id, TexList.name_mode(self.name))
return '{self.parent.href_id}:{self.name}'.format(self=self)
return self.name
def format(items):
tex = TexList()
#Logger.instance().info('Processing items...')
for item in items:
# do no format certain objects
#Logger.instance().info('processing: %s (%s)' % (item, item.href_id))
if not item.include_in_format():
#Logger.instance().info(' - skipped')
continue
#Logger.instance().info(' +++ formatting +++')
fmt = LatexFormatter.get_formatter_for(item)
if fmt is not None:
fmt.format(item)
tex.extend(fmt)
return tex
def __init__(self, element):
if type(element) in (str, unicode):
tree = ET.fromstring('<html_example>' + element + "</html_example>")
self.el = tree
else:
self.el = element
from ist.utils.texlist2 import TexList
self.tex = TexList()
def parse2latex(self, md_text):
from ist.utils.texlist2 import TexList
reduce_tag = 'div'
secured_markdown = self._replace_math(md_text)
latex_secured = TexList.prepare_plain(secured_markdown)
# apply markdown
html_secured = markdown.markdown(latex_secured, extensions=[
'markdown.extensions.sane_lists',
'markdown.extensions.nl2br',
'ist.formatters.extensions.md_links',
'ist.formatters.extensions.md_strike'])
html_secured = TexList.finish_plain(html_secured)
html = self._md_latex.finish(html_secured)
try:
return ET.fromstring(html)
except Exception as e:
return ET.fromstring('<' + reduce_tag + '>' + html + '</' + reduce_tag + '>')
def parse2latex(self, md_text):
from ist.utils.texlist2 import TexList
reduce_tag = 'div'
secured_markdown = self._replace_math(md_text)
latex_secured = TexList.prepare_plain(secured_markdown)
# apply markdown
html_secured = markdown.markdown(latex_secured, extensions=[
'markdown.extensions.sane_lists',
'markdown.extensions.nl2br',
'ist.formatters.extensions.md_links',
'ist.formatters.extensions.md_strike'])
html_secured = TexList.finish_plain(html_secured)
html = self._md_latex.finish(html_secured)
try:
return ET.fromstring(html)
except Exception as e:
return ET.fromstring('<' + reduce_tag + '>' + html + '</' + reduce_tag + '>')
def format(items):
tex = TexList()
Logger.instance().info('Processing items...')
for item in items:
# do no format certain objects
if not item.include_in_format():
Logger.instance().info(' - item skipped: %s' % str(item))
continue
Logger.instance().info(' - formatting item: %s' % str(item))
# l = LatexRecord()
# l.format(item)
# print l
# exit()
fmt = LatexFormatter.get_formatter_for(item)
if fmt is not None:
fmt.format(item)
tex.extend(fmt)
return tex
def format(items):
tex = TexList()
Logger.instance().info('Processing items...')
for item in items:
# do no format certain objects
if not item.include_in_format():
Logger.instance().info(' - item skipped: %s' % str(item))
continue
Logger.instance().info(' - formatting item: %s' % str(item))
# l = LatexRecord()
# l.format(item)
# print l
# exit()
fmt = LatexFormatter.get_formatter_for(item)
if fmt is not None:
fmt.format(item)
tex.extend(fmt)
return tex
def format(items):
tex = texlist()
Logger.instance().info('Processing items...')
for item in items:
# do no format certain objects
if not item.include_in_format():
Logger.instance().info(' - item skipped: %s' % str(item))
continue
Logger.instance().info(' - formatting item: %s' % str(item))
a = TexList()
a.macro_record_type(item)
print a
exit()
fmt = LatexFormatter.get_formatter_for(item)
if fmt is not None:
tex.extend(fmt.format(item))
tex.newline()
tex.newline()
return tex
def href_id(self):
"""
Method will return unique id of this item
if link_name was specified in attributes, it will be used
:return:
"""
if getattr(self, 'attributes', None) and self.attributes.link_name:
value = self.attributes.link_name
else:
value = self.get('unique_name', 'name', 'id')
if FormatMode.format_mode == FormatMode.LATEX_MODE:
return 'IT::{}'.format(TexList.name_mode(value))
return htmltree.secure(value)
def href_id(self):
"""
Method will return unique id of this item
if link_name was specified in attributes, it will be used
:return:
"""
if getattr(self, 'attributes', None) and self.attributes.link_name:
value = self.attributes.link_name
else:
value = self.get('unique_name', 'name', 'id')
if FormatMode.format_mode == FormatMode.LATEX_MODE:
return 'IT::{}'.format(TexList.name_mode(value))
return htmltree.secure(value)
class Html2Latex(object):
"""
Class which based on given element (html/string) can produce latex format
"""
list_types = {
'ul': 'itemize',
'ol': 'enumerate'
}
def __init__(self, element):
if type(element) in (str, unicode):
tree = ET.fromstring('<html_example>' + element + "</html_example>")
self.el = tree
else:
self.el = element
from ist.utils.texlist2 import TexList
self.tex = TexList()
def extend_children(self):
"""
Recursive children call
"""
for child in self.el:
self.tex.extend(Html2Latex(child).to_latex())
def tag_is(self, *tags):
"""
whether current tag is in given tags
"""
return self.el.tag in tags
def text(self):
""" return current text """
return self.el.text if self.el.text else ''
def tail(self):
""" return current tail """
return self.el.tail if self.el.tail else ''
def add_text(self):
if str(self.text).strip():
with self.tex:
self.tex.append(self.text())
def add_tail(self):
"""
Adds current tail if exists
"""
if self.tail():
if self.tail() == '\n':
self.tex.append(self.tail())
else:
with self.tex:
self.tex.append(self.tail())
def get_list_type(self):
""" helper method for getting list type"""
return self.list_types.get(self.el.tag, 'itemize')
#
# def tag (self):
# return self.el.tag
def to_latex(self):
"""
Method converts this object to latex with recursive calls
"""
if self.tag_is('p'):
with self.tex:
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
# self.tex.newline ()
elif self.tag_is('br'):
self.tex.append(self.text())
self.tex.append(r'\\')
self.extend_children()
self.add_tail()
elif self.tag_is('h1'):
self.tex.append('\\section')
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
elif self.tag_is('a'):
self.tex.extend(LatexHref(self.el).to_latex())
elif self.tag_is('em'):
self.tex.append('\\textit')
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
elif self.tag_is('strong'):
self.tex.append('\\textbf')
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
elif self.tag_is('ul', 'ol'):
self.tex.begin(self.get_list_type())
self.tex.append(self.text())
self.extend_children()
self.tex.end(self.get_list_type())
self.add_tail()
elif self.tag_is('li'):
# with self.tex:
self.tex.append('\\item ')
self.add_text()
self.extend_children()
self.add_tail()
# so far, code tag will be monospaced only
elif self.tag_is('code'):
# self.tex.open_element ('lstlisting')
# self.tex.newline ()
self.tex.slash('ttfamily ')
self.tex.append(self.text().replace('\$', '\$'))
# self.extend_children ()
# self.tex.newline ()
# self.tex.close_element ('lstlisting')
# self.add_tail ()
elif self.tag_is('span'):
self.tex.append(self.text())
self.extend_children()
self.add_tail()
else:
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
return self.tex
class Html2Latex(object):
"""
Class Html2Latex which based on given element (html/string) can produce latex format
"""
list_types = {
'ul': 'itemize',
'ol': 'enumerate'
}
def __init__(self, element):
if type(element) in (str, unicode):
tree = ET.fromstring('<html_example>' + element + "</html_example>")
self.el = tree
else:
self.el = element
from ist.utils.texlist2 import TexList
self.tex = TexList()
def extend_children(self):
"""
Recursive children call
"""
for child in self.el:
self.tex.extend(Html2Latex(child).to_latex())
def tag_is(self, *tags):
"""
whether current tag is in given tags
"""
return self.el.tag in tags
def text(self):
""" return current text """
return self.el.text if self.el.text else ''
def tail(self):
""" return current tail """
return self.el.tail if self.el.tail else ''
def add_text(self):
if str(self.text).strip():
with self.tex:
self.tex.append(self.text())
def add_tail(self):
"""
Adds current tail if exists
"""
if self.tail():
if self.tail() == '\n':
self.tex.append(self.tail())
else:
with self.tex:
self.tex.append(self.tail())
def get_list_type(self):
""" helper method for getting list type"""
return self.list_types.get(self.el.tag, 'itemize')
#
# def tag (self):
# return self.el.tag
def to_latex(self):
"""
Method converts this object to latex with recursive calls
"""
if self.tag_is('p'):
with self.tex:
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
# self.tex.newline ()
elif self.tag_is('br'):
self.tex.append(self.text())
self.tex.append(r'\\')
self.extend_children()
self.add_tail()
elif self.tag_is('h1'):
self.tex.append('\\section')
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
elif self.tag_is('a'):
self.tex.extend(LatexHref(self.el).to_latex())
elif self.tag_is('em'):
self.tex.append('\\textit')
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
elif self.tag_is('strong'):
self.tex.append('\\textbf')
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
elif self.tag_is('ul', 'ol'):
self.tex.begin(self.get_list_type())
self.tex.append(self.text().strip())
self.extend_children()
self.tex.end(self.get_list_type())
self.add_tail()
elif self.tag_is('li'):
# with self.tex:
self.tex.append('\\item ')
self.add_text()
self.extend_children()
self.add_tail()
# so far, code tag will be monospaced only
elif self.tag_is('code'):
# self.tex.open_element ('lstlisting')
# self.tex.newline ()
self.tex.slash('ttfamily ')
self.tex.append(self.text().replace('\$', '\$'))
# self.extend_children ()
# self.tex.newline ()
# self.tex.close_element ('lstlisting')
# self.add_tail ()
elif self.tag_is('span'):
self.tex.append(self.text())
self.extend_children()
self.add_tail()
else:
with self.tex:
self.tex.append(self.text())
self.extend_children()
self.add_tail()
return self.tex