def save_css(soup, fo, assets_dir):
"""
Extracts <style> elements in <head> from the
file and replaces them with <link>.
"""
n = 0
for style in soup.select('head style'):
data = style.text.encode(errors='ignore')
md5 = get_md5(data)
basename = 'style-%s.css' % md5
dest_abs = os.path.join(assets_dir, basename)
dest_rel = os.path.relpath(dest_abs, os.path.dirname(fo))
if not os.path.exists(dest_abs):
make_sure_dir_exists(dest_abs)
with open(dest_abs, 'w') as f:
f.write(data)
link = Tag(name='link')
link.attrs['rel'] = 'stylesheet'
link.attrs['type'] = 'text/css'
link.attrs['href'] = dest_rel
style.replace_with(link)
n += 1
return n
def extract_assets_from_file(fi, fo, assets_dir):
# logger.info('Extracting assets ___')
# logger.info('Input: %s' % fi)
# logger.info('Output: %s' % fo)
# logger.info('Using assets dir: %s' % assets_dir)
make_sure_dir_exists(fo)
if not os.path.exists(assets_dir):
os.makedirs(assets_dir)
soup = read_html_doc_from_file(fi)
s0 = os.path.getsize(fi)
def savefile(filename_hint, data):
""" must return the url (might be equal to filename) """
where = os.path.join(assets_dir, filename_hint)
write_data_to_file(data, where)
relative = os.path.relpath(where, os.path.dirname(fo))
return relative
extract_img_to_file(soup, savefile)
write_html_doc_to_file(soup, fo)
if False:
s1 = os.path.getsize(fo)
inmb = lambda x: '%.1f MB' % (x / (1024.0 * 1024))
msg = 'File size: %s -> %s' % (inmb(s0), inmb(s1))
logger.info(msg)
def write_data_to_file(data, filename, quiet=False):
"""
Writes the data to the given filename.
If the data did not change, the file is not touched.
"""
if not isinstance(data, bytes):
msg = 'Expected "data" to be bytes, not %s.' % type(data).__name__
raise ValueError(msg)
if len(filename) > 256:
msg = 'Invalid argument filename: too long. Did you confuse it with data?'
raise ValueError(msg)
make_sure_dir_exists(filename)
if os.path.exists(filename):
current = open(filename).read()
if current == data:
if not 'assets' in filename:
if not quiet:
logger.debug('already up to date %s' % friendly_path(filename))
return
with open(filename, 'wb') as f:
f.write(data)
if not quiet:
logger.debug('Written to: %s' % friendly_path(filename))
def extract_assets_from_file(data, fo, assets_dir):
res = AugmentedResult()
make_sure_dir_exists(fo)
if not os.path.exists(assets_dir):
mkdirs_thread_safe(assets_dir)
soup = bs_entire_document(data)
def savefile(filename_hint, data_):
""" must return the url (might be equal to filename) """
where = os.path.join(assets_dir, filename_hint)
write_data_to_file(data_, where, quiet=True)
relative = os.path.relpath(where, os.path.dirname(fo))
return relative
from mcdp_report.embedded_images import extract_img_to_file
nimg = extract_img_to_file(soup, savefile)
nsave = save_images_locally(soup, fo, assets_dir)
ncss = save_css(soup, fo, assets_dir)
n = nimg + nsave + ncss
if n:
pass
# print('Total of %d subs (img %d save %d css %d)' % (n, nimg, nsave, ncss))
write_html_doc_to_file(soup, fo, quiet=True)
return res
def pdf2svg(f1, f2):
make_sure_dir_exists(f2)
cwd = '.'
cmd = ['pdf2svg', f1, f2]
_res = system_cmd_result(cwd, cmd,
display_stdout=False,
display_stderr=False,
raise_on_error=True)
def extract_page(filename, page, output):
make_sure_dir_exists(output)
cwd = '.'
cmd = ['pdftk', filename, 'cat', str(page), 'output', output]
_res = system_cmd_result(cwd, cmd,
display_stdout=False,
display_stderr=False,
raise_on_error=True)
def update_graph(context, event):
print('event: %s' % event)
if event.name in ['manager-job-starting']:
job_id = event.kwargs['job_id']
Global.processing.add(job_id)
if event.name in ['manager-job-failed', 'manager-job-succeeded']:
job_id = event.kwargs['job_id']
Global.processing.remove(job_id)
print('global processing %s' % Global.processing)
if 'job_id' in event.kwargs:
what = '%s-%s' % (event.name, event.kwargs['job_id'])
else:
what = event.name
filename = os.path.join(Global.dirname,
('step-%04d-%s' % (Global.step, what)))
make_sure_dir_exists(filename)
# print('step %d: jobs = %s' % (Global.step, Global.job_list))
graph(job_list=list(Global.job_list),
context=context,
filename=filename,
processing=Global.processing,
**Global.graph_params)
Global.step += 1
# see here:
# http://stackoverflow.com/questions/14784405/how-to-set-the-output-size-in-graphviz-for-the-dot-format
png = filename + ".png"
png2 = filename + "-x.png"
size = Global.size
dpi = Global.dpi
cmd0 = [
'dot', '-Tpng',
'-Gsize=%s,%s\!' % (size[0] / dpi, size[1] / dpi),
'-Gdpi=%s' % dpi, '-o' + png, filename
]
system_cmd_result('.',
cmd0,
display_stdout=True,
display_stderr=True,
raise_on_error=True)
cmd = [
'convert', png, '-gravity', 'center', '-background', 'white',
'-extent',
'%sx%s' % (size[0], size[1]), png2
]
system_cmd_result('.',
cmd,
display_stdout=True,
display_stderr=True,
raise_on_error=True)
os.unlink(png)
def pdfcrop_margins(f1, f2, margins):
make_sure_dir_exists(f2)
cwd = '.'
cmd = ['pdfjam', '--keepinfo', '--trim', margins,
'--paper', 'letter', '--landscape',
'--clip', 'true', '--outfile', f2, f1]
# cmd = ['pdfcrop', f1, '--margins', str(margins), f2]
_res = system_cmd_result(cwd, cmd,
display_stdout=False,
display_stderr=False,
raise_on_error=True)
def test_toc_numbers1():
s = r"""
<div id='toc'></div>
# Part One {#part:one}
# Chapter One
## Sub One_point_One
Referring to [](#fig:One) and [](#fig:Two) and [](#tab:One).
Also referring only with numbers:
<a href="#fig:One" class='only_number'></a>,
<a href="#fig:Two" class='only_number'></a>,
<a href="#tab:One" class='only_number'></a>.
<s figure-id="fig:One">Figure One</s>
### Sub sub One_point_One_point_One
#### Par a
#### Par b
## Sub One_point_Two
Referring to subfigures [](#subfig:child1) and [](#subfig:child2).
<div figure-id="fig:parent">
<div figure-id="subfig:child1" figure-caption="child1">
child1
</div>
<div figure-id="subfig:child2" figure-caption="child2">
child2
</div>
</div>
<div figure-id="code:code1">
<pre><code>code1</code></pre>
</div>
## Sub with `code` in the <k>name</k>
# Chapter Two
<s figure-id="fig:Two">Figure Two</s>
<s figure-id="tab:One">Table One</s>
## Sub Two_point_One
# Part Two {#part:two}
# Chapter Three
\begin{definition}[DefinitionA]\label{def:A}Definition A\end{definition}
\begin{defn}[DefinitionA2]\label{def:A2}Definition A2\end{defn}
\begin{proposition}[PropositionB]\label{prop:B}Proposition B\end{proposition}
\begin{problem}[ProblemC]\label{prob:C}Problem C\end{problem}
\begin{example}[exampleD]\label{exa:D}...\end{example}
\begin{remark}[remarkE]\label{rem:E}...\end{remark}
\begin{lemma}[lammaF]\label{lem:F}...\end{lemma}
\begin{theorem}[theoremG]\label{thm:G}...\end{theorem}
\begin{thm}[theoremG2]\label{thm:G2}...\end{thm}
Citing:
[](#def:A),
[](#prop:B),
[](#prob:C),
[](#exa:D),
[](#rem:E),
[](#lem:F),
[](#thm:G).
Citing full name:
<a href="#def:A" class="number_name"></a>,
<a href="#prop:B" class="number_name"></a>,
<a href="#prob:C" class="number_name"></a>,
<a href="#exa:D" class="number_name"></a>,
<a href="#rem:E" class="number_name"></a>,
<a href="#lem:F" class="number_name"></a>,
<a href="#thm:G" class="number_name"></a>.
Citing only name:
<a href="#def:A" class="only_name"></a>,
<a href="#prop:B" class="only_name"></a>,
<a href="#prob:C" class="only_name"></a>,
<a href="#exa:D" class="only_name"></a>,
<a href="#rem:E" class="only_name"></a>,
<a href="#lem:F" class="only_name"></a>,
<a href="#thm:G" class="only_name"></a>.
Citing only number:
<a href="#def:A" class="only_number"></a>,
<a href="#prop:B" class="only_number"></a>,
<a href="#prob:C" class="only_number"></a>,
<a href="#exa:D" class="only_number"></a>,
<a href="#rem:E" class="only_number"></a>,
<a href="#lem:F" class="only_number"></a>,
<a href="#thm:G" class="only_number"></a>.
# Appendices {#part:appendices}
# Appendix A {#app:A}
# Appendix B {#app:B}
## App sub B_point_One
### App subsub B_point_One_point_One
"""
library = MCDPLibrary()
raise_errors = True
realpath = __name__
s = render_complete(library, s, raise_errors, realpath)
files_contents = [DocToJoin(docname='a', contents=s, source_info=None)]
stylesheet = 'v_manual_blurb_ready'
res = manual_join(template=template,
files_contents=files_contents,
stylesheet=stylesheet)
fn = 'out/comptests/test_toc_numbers1.html' # XXX: write on test folder
make_sure_dir_exists(fn)
logger.info('written on %s' % fn)
with open(fn, 'w') as f:
f.write(res)
def update_graph(context, event):
print('event: %s' % event)
if event.name in ['manager-job-starting']:
job_id = event.kwargs['job_id']
Global.processing.add(job_id)
if event.name in ['manager-job-failed',
'manager-job-succeeded']:
job_id = event.kwargs['job_id']
Global.processing.remove(job_id)
print('global processing %s' % Global.processing)
if 'job_id' in event.kwargs:
what = '%s-%s' % (event.name, event.kwargs['job_id'])
else:
what = event.name
filename = os.path.join(Global.dirname,
('step-%04d-%s' % (Global.step, what)))
make_sure_dir_exists(filename)
# print('step %d: jobs = %s' % (Global.step, Global.job_list))
graph(job_list=list(Global.job_list),
context=context,
filename=filename,
processing=Global.processing,
**Global.graph_params)
Global.step += 1
# see here:
# http://stackoverflow.com/questions/14784405/how-to-set-the-output-size-in-graphviz-for-the-dot-format
png = filename + ".png"
png2 = filename + "-x.png"
size = Global.size
dpi = Global.dpi
cmd0 = ['dot', '-Tpng',
'-Gsize=%s,%s\!' % (size[0]/dpi, size[1]/dpi),
'-Gdpi=%s' % dpi,
'-o' + png, filename]
system_cmd_result(
'.', cmd0,
display_stdout=True,
display_stderr=True,
raise_on_error=True)
cmd=['convert',
png,
'-gravity',
'center',
'-background',
'white',
'-extent',
'%sx%s' % (size[0], size[1]),
png2]
system_cmd_result(
'.', cmd,
display_stdout=True,
display_stderr=True,
raise_on_error=True)
os.unlink(png)
