def test_parse_html2(self):
parser = QqParser(
allowed_tags={
'chapter', 'section', 'subsection', 'subsubsection', 'eq',
'eqref', 'ref', 'equation', 'label', 'idx'
})
doc = r"""\chapter \label h1:label
Hello
This is a \ref{h1:label}.
"""
tree = parser.parse(doc)
html = QqHTMLFormatter(tree)
s = html.do_format()
soup = BeautifulSoup(s, 'html.parser')
self.assertEqual(soup.h1['id'], 'label_h1_label')
self.assertEqual(soup.span['class'], ['section__number'])
self.assertEqual(soup.span.string, "1")
self.assertEqual(
soup("a")[1].attrs, {
'class': ['a-ref'],
'title': '',
'href': '#label_h1_label'
})
self.assertEqual(soup("a")[1].string, "1")
def test_extract_toc(self):
doc = dedent(r"""
\section haha
\chapter Chap-One
Hello
\section Sec-One
World
\section Sec-Two
This
\subsection SubSec-One
Lala
\subsection SubSec-Two
Qqq
\section Sec-Three
Dada
\chapter Chap-Two
\subsection Strange
\section Last
""")
parser = QqParser()
formatter = QqHTMLFormatter()
parser.allowed_tags.update(formatter.uses_tags())
tree = parser.parse(doc)
formatter.root = tree
toc = formatter.extract_toc(maxlevel=3)
self.assertEqual(
toc.as_tuple(),
(None, [(None, [('section', [])]),
('chapter', [('section', []),
('section', [('subsection', []),
('subsection', [])]),
('section', [])]),
('chapter', [(None, [('subsection', [])]),
('section', [])])]))
def test_parse_html1(self):
parser = QqParser(
allowed_tags={
'chapter', 'section', 'subsection', 'subsubsection', 'eq',
'eqref', 'ref', 'equation', 'label', 'idx'
})
doc = r"""\chapter
Hello
\label
h1:label
\section
World
"""
tree = parser.parse(doc)
html = QqHTMLFormatter(tree)
s = html.do_format()
print(s)
soup = BeautifulSoup(s, 'html.parser')
#self.assertEqual(s, """<h1 id="label_h1_label"><span class="section__number"><a href="#label_h1_label" class="section__number">1</a></span>Hello
#</h1><h2 id="label_h2_number_1_1"><span class="section__number"><a href="#label_h2_number_1_1" class="section__number">1.1</a></span>World
#</h2>""")
self.assertEqual('label_h1_label', soup.h1['id'])
self.assertEqual(['section__number'], soup.span['class'])
self.assertEqual('#label_h1_label', soup.a['href'])
self.assertEqual(['section__number'], soup.a['class'])
self.assertEqual('1Hello', soup.h1.text.strip())
self.assertEqual('1.1World', soup.h2.text.strip())
def test_parse_html_math_align(self):
html = QqHTMLFormatter()
parser = QqParser(allowed_tags=html.uses_tags())
doc = r"""\align
\item c^2 &= a^2 + b^2 \label eq:one
\item c &= \sqrt{a^2 + b^2} \label eq:two
See \ref{eq:one} and \ref{eq:two}
"""
tree = parser.parse(doc)
html.root = tree
html.counters['equation'].showparents = False
s = html.do_format()
soup = BeautifulSoup(s, 'html.parser')
print(repr(soup.text))
self.assertEqual(
soup.text,
"\\[\n\\begin{align}\n\nc^2 &= a^2 + b^2 \n\\tag{1}\n\\\\\n"
"c &= \\sqrt{a^2 + b^2} \n\\tag{2}\n\\\\\n\\end{align}\n\\]\n\n\n\nSee (1) and (2)"
)
self.assertEqual(soup.a['href'], "#mjx-eqn-1")
self.assertEqual(soup.a.string, "(1)")
self.assertEqual(soup("a")[1]['href'], "#mjx-eqn-2")
self.assertEqual(soup("a")[1].string, "(2)")
def show(lang, filename):
parser = QqParser()
parser.allowed_tags.update(allowed_tags)
source_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"source")
path = os.path.join(source_dir, "contents.qq")
tree = parser.parse_file(path).process_include_tags(parser, source_dir)
if filename:
topic = [t for t in tree.find_all("topic")
if t._id.value == filename][0]
else:
topic = tree._topic
for compare in topic.find_all("compare"):
for prlang in ['python', 'js']:
for prlangtag in compare.find_all(prlang):
pr = process_prlang(prlangtag, prlang)
prlangtag.clear()
prlangtag.extend_children(pr)
def get_tag_lang(tree, tagname):
first = None
default_lang = None
for tag in tree.find_all(tagname):
if tag._lang and tag._lang.value == lang:
return tag
if first is None:
first = tag
if tag._lang == DEFAULT_LANG and default_lang is None:
default_lang = tag
if default_lang:
return default_lang
return first
if lang == 'en':
def translate(s):
return s
elif lang == 'ru':
def translate(s):
return translations.get(s, s)
return render_template("py_js_compare.html",
lang=lang,
tree=tree,
topic=topic,
translate=translate,
mistune=mistune,
get_tag_lang=get_tag_lang)
def parse_and_format(doc: str,
formatter_factory,
allowed_tags = None) -> str:
formatter = formatter_factory()
if allowed_tags is None:
allowed_tags = formatter.uses_tags()
parser = QqParser(allowed_tags=allowed_tags)
tree = parser.parse(doc)
formatter.root = tree
return formatter.do_format()
def prepare_book():
global wholebook
if app.config.get("freeze"):
global tree
global formatter
if wholebook is not None:
return tree, formatter
path = os.path.join(curdir, app.config["FILE"])
if not os.path.isfile(path):
abort(404)
with open(path) as f:
lines = f.readlines()
parser = QqParser()
formatter = QqFlaskHTMLFormatter(
eq_preview_by_labels=not app.config.get("MATHJAX_WHOLEBOOK"))
parser.allowed_tags.update(formatter.uses_tags())
parser.allowed_tags.add("idx") # for indexes
tree = parser.parse(lines).process_include_tags(parser, curdir)
formatter.root = tree
formatter.pythonfigure_globals.update({"ob": odebook, "np": numpy})
formatter.code_prefixes["pythonfigure"] += (
"import numpy as np\n"
"import qqmbr.odebook as ob\n"
"# see https://github.com/ischurov/qqmbr/blob/master/qqmbr/odebook.py"
"\n\n")
formatter.code_prefixes["pythonvideo"] = formatter.code_prefixes[
"pythonfigure"]
formatter.plotly_globals.update({"np": numpy})
formatter.code_prefixes["plotly"] = (
formatter.code_prefixes.get("plotly", "") + "import numpy as np\n\n")
formatter.mode = "bychapters"
formatter.make_numbers(tree)
formatter.make_chapters()
# dirty hack to get equation snippet work
if wholebook is None:
if app.config.get("MATHJAX_WHOLEBOOK"):
style, wholebook = mathjax(
get_preamble(tree) + formatter.format(tree))
else:
wholebook = formatter.format(tree)
style = ""
app.config["css_correction"] = style + app.config.get("css_correction")
return tree, formatter
def test_ref_with_separator(self):
doc = r"""\chapter Hello \label sec:first
See \ref[section][sec:first] for details.
"""
parser = QqParser()
formatter = QqHTMLFormatter()
parser.allowed_tags.update(formatter.uses_tags())
tree = parser.parse(doc)
formatter.root = tree
html = formatter.do_format()
soup = BeautifulSoup(html, "html.parser")
self.assertEqual(soup("a")[1]['href'], "#label_sec_first")
self.assertEqual(soup("a")[1].string, "section 1")
def test_refs_with_separator(self):
doc = r"""\chapter Hello \label sec:first
\chapter World \label sec:other
See
\ref[section][sec:first] and \ref[section][sec:other] for details.
"""
parser = QqParser()
formatter = QqHTMLFormatter()
parser.allowed_tags.update(formatter.uses_tags())
tree = parser.parse(doc)
formatter.root = tree
print(tree.as_list())
html = formatter.do_format()
soup = BeautifulSoup(html, "html.parser")
self.assertEqual(soup("a")[2].contents[0], "section 1")
def render():
text = request.values.get('text', '').replace('\r\n', '\n')
formatter = QqHTMLFormatter()
formatter.localnames = {}
parser = QqParser(allowed_tags=formatter.safe_tags)
try:
tree = parser.parse(text)
except Exception as e:
return jsonify(error='parse error: ' + str(e))
formatter.root = tree
try:
output = formatter.do_format()
except Exception as e:
return jsonify(error='format error: ' + str(e))
return jsonify(output=output)
def show_snippet(label):
tree, formatter = prepare_book()
tag = formatter.label_to_tag.get(label)
if tag is None or tag.name != 'snippet':
abort(404)
if tag.exists("backref"):
backref = tag.backref_.value
else:
backref = label
parser = QqParser()
parser.allowed_tags.update(formatter.uses_tags())
backref_tag = parser.parse(r"\ref[Подробнее\nonumber][{}]".format(backref))
tag.append_child(backref_tag.ref_)
html = formatter.format(tag, blanks_to_pars=True)
return mathjax_if_needed(html)[1]
def convert(**args):
path = os.path.join(curdir, app.config["FILE"])
with open(path) as f:
lines = f.readlines()
formatter = QqHTMLFormatter()
parser = QqParser(allowed_tags=formatter.uses_tags())
try:
tree = parser.parse(lines)
except Exception as e:
print("Parse error:", str(e))
raise
formatter.root = tree
try:
output = formatter.do_format()
except Exception as e:
print("Formatting error:", str(e))
raise
print(output)
def test_parse_html3(self):
parser = QqParser(
allowed_tags={
'h1', 'h2', 'h3', 'h4', 'eq', 'eqref', 'ref', 'equation',
'label', 'idx'
})
doc = r"""\equation \label eq:x2y2
x^2 + y^2 = z^2
See \ref{eq:x2y2}.
"""
tree = parser.parse(doc)
html = QqHTMLFormatter(tree)
html.counters['equation'].showparents = False
s = html.do_format()
soup = BeautifulSoup(s, 'html.parser')
self.assertEqual(soup.div.attrs, {
'id': "label_eq_x2y2",
'class': ["latex_equation"]
})
self.assertEqual(soup.span['class'], ['ref'])
self.assertEqual(soup.a['class'], ['a-ref'])
self.assertEqual(soup.a['href'], '#mjx-eqn-1')
self.assertEqual(soup.a.string, "(1)")
def test_tag2chapter(self):
html = QqHTMLFormatter()
parser = QqParser(allowed_tags=html.uses_tags())
parser.allowed_tags.add('author')
doc = r"""\author Ilya V. Schurov
\chapter Chapter 1
This is the first chapter
\equation \label eq1
x^2 + y^2
\chapter Chapter 2
This is the second chapter
\section Section 1
Hello
\remark \label rem
This is the end. \ref{eq1}
"""
tree = parser.parse(doc)
html.root = tree
self.assertEqual(html.tag2chapter(tree.author_), 0)
self.assertEqual(html.tag2chapter(tree.equation_), 1)
self.assertEqual(html.tag2chapter(tree.equation_.label_), 1)
self.assertEqual(html.tag2chapter(tree.remark_), 2)
self.assertEqual(html.tag2chapter(tree.remark_.ref_), 2)
def render(path):
print(path_to_source_url(path))
r = requests.get(path_to_source_url(path))
r.encoding = 'UTF-8'
if not r:
abort(500)
formatter = QqHTMLFormatter(with_chapters=False)
formatter.localnames = {}
parser = QqParser(allowed_tags=formatter.safe_tags)
try:
tree = parser.parse(r.text)
except Exception as e:
if app.debug:
raise e
return render_template("error.html",
error='parse error: ' + str(e)), 400
formatter.root = tree
try:
output = formatter.do_format()
except Exception as e:
if app.debug:
raise e
return render_template("error.html",
error='format error: ' + str(e)), 400
meta = tree.find_or_empty("meta")
print(meta.as_list())
return render_template("render_url.html",
output=output,
source_url=path_to_url(path),
meta=meta)