def add_to_output(html_doc, para):
global new_lines_in_raw
# we shouldn't accept empty paragraph (?)
assert len(para) > 0
with html_doc.body.children[-1]:
assert html_doc.body.children[-1]['class'] == 'container-fluid'
for (i, (type, text)) in enumerate(para):
if 'heading' in type and text.strip():
# tags.p()
# tags.p()
heading = sizes.get_heading_type(size_kind)
print type, text
heading(text)
elif type == "new_line":
new_lines_in_raw += 1
if new_lines_in_raw == 1:
tags.br()
elif new_lines_in_raw == 2:
tags.p()
else:
pass
elif is_subject(para, i):
if not is_prev_subject(para, i):
# tags.p()
#tags.br()
pass
subject(html_doc, type, text)
else:
regular(type, text)
if type != "new_line":
new_lines_in_raw = 0
def add_to_output(html_doc, para):
global new_lines_in_raw
# we shouldn't accept empty paragraph (?)
assert len(para) > 0
with html_doc.body.children[-1]:
assert html_doc.body.children[-1]['class'] == 'container-fluid';
for (i, (type, text)) in enumerate(para):
if 'heading' in type and text.strip():
# tags.p()
# tags.p()
heading = sizes.get_heading_type(size_kind)
print type, text
heading(text)
elif type == "new_line":
new_lines_in_raw += 1
if new_lines_in_raw == 1:
tags.br()
elif new_lines_in_raw == 2:
tags.p()
else:
pass
elif is_subject(para, i):
if not is_prev_subject(para, i):
# tags.p()
#tags.br()
pass
subject(html_doc, type, text)
else:
regular(type, text)
if type != "new_line":
new_lines_in_raw = 0
def add_images(self, ims, txts, links, width=400):
"""add images to the HTML file
Parameters:
ims (str list) -- a list of image paths
txts (str list) -- a list of image names shown on the website
links (str list) -- a list of hyperref links; when you click an image, it will redirect you to a new page
"""
self.t = table(border=1,
style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;",
halign="center",
valign="top"):
with p():
with a(href=os.path.join('images', link)):
#img(style="width:%dpx" % width, src=os.path.join('images', im))
img(style="width:%dpx" % width,
src=os.path.join(self.folder, im))
br()
p(txt)
def test_other(self):
c = Converter('Man', file='diff.man')
c.translate()
text = c.html.render()
text = c.change_special_symbols(text)
doc = tags.html(lang='en')
doc = add_head(doc)
doc_body = tags.body()
row = tags.div(cls='row')
row = add_row(row, 'GCC(1)', '', 'GCC(1)')
doc_body.add(row)
with doc_body:
paragraph = tags.p()
paragraph.add(tags.br())
paragraph.add('\n\\f(CW c c-header cpp-output\\fP')
paragraph.add(tags.br())
paragraph.add(tags.br())
def_list = tags.dl()
def_termin = tags.dt()
def_termin.add('\n')
def_termin.add('\\fB-x none\\fR')
def_def = tags.dd(cls='indent')
def_def.add('\nstandard_output.')
def_list.add(def_termin)
def_list.add(def_def)
row = tags.div(cls='row')
row = add_row(row, '', '2018-07-20', 'GCC(1)')
doc_body.add(row)
doc.add(doc_body)
doc = c.change_special_symbols(doc.render())
self.assertEqual(doc, text)
def test_many_argument_strings(self):
c = Converter('Man', file='links.man')
c.translate()
text = c.html.render()
text = c.change_special_symbols(text)
doc = tags.html(lang='en')
doc = add_head(doc)
doc_body = tags.body()
row = tags.div(cls='row')
row = add_row(row, 'GREP(1)', 'User Commands', 'GREP(1)')
doc_body.add(row)
with doc_body:
paragraph = tags.p()
paragraph += (tags.a('the bug-reporting address',
href='mailto:[email protected]'))
paragraph += tags.br()
paragraph += (tags.a(
'email archive',
href='http://lists.gnu.org/mailman/listinfo/bug-grep'))
paragraph += tags.br()
paragraph += tags.br()
row = tags.div(cls='row')
row = add_row(row, 'GNU grep 3.1', '2017-06-21', 'GREP(1)')
doc_body.add(row)
doc.add(doc_body)
self.assertEqual(doc.render(), text)
def add_images(self, epoch, ims, txts, links, width=400):
if epoch != -1:
img_dir_epoch = os.path.join(self.img_dir, str(epoch))
util.mkdirs(img_dir_epoch)
else:
img_dir_epoch = self.img_dir
path_parts = img_dir_epoch.split('/')
if self.is_test:
rel_path = path_parts[-1:]
else:
rel_path = path_parts[-2:]
rel_path = '/'.join(rel_path)
self.add_table()
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;",
halign="center",
valign="top"):
with p():
with a(href=os.path.join(rel_path, link)):
img(style="width:%dpx" % width,
src=os.path.join(rel_path, im))
br()
p(txt)
def add_images(self, ims, txts, links, width=400):
"""add images to the HTML file
Parameters:
ims (str list) -- a list of image paths
txts (str list) -- a list of image names shown on the website
links (str list) -- a list of hyperref links; when you click an image, it will redirect you to a new page
"""
self.t = table(border=1,
style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;",
halign="center",
valign="top"):
with p():
with a(href=link):
img(style="width:%dpx" % width, src=im)
br()
# attrs_path = os.path.join(self.web_dir,'attributes', txt)
# with open(attrs_path, "r") as attr_log_file:
# attrs_str =attr_log_file.read() # save the message
# attrs_str.replace('\n','<br>')
text(txt)
def add_image(self,
im,
title,
txt='',
width=None,
height=None,
font_pct=100):
if width is None:
width = self.default_image_width
if height is None:
height = self.default_image_height
if self.t is None or self.row_image_count >= self.images_per_row:
self._add_table()
with self.t:
# with tr():
# with td(style="word-wrap: break-word;", halign="center", valign="top"):
with tags.td(halign="center", valign="top"):
with tags.p():
if height is not None:
img_style = "width:{}px; height:{}px".format(
width, height)
else:
img_style = "width:{}px;".format(width)
tags.img(style=img_style,
src=r'data:image/png;base64,' +
self._encode_image(im))
tags.br()
tags.p(
"{}\n{}".format(title, txt),
style=
'width:{}px; word-wrap: break-word; white-space: pre-wrap; font-size: {}%;'
.format(width, font_pct))
self.row_image_count += 1
def add_videos(self, vids, txts, links, width=400):
"""add images to the HTML file
Parameters:
ims (str list) -- a list of image paths
txts (str list) -- a list of image names shown on the website
links (str list) -- a list of hyperref links; when you click an image, it will redirect you to a new page
"""
self.t = table(border=1,
style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
with self.t:
with tr():
for vid, txt, link in zip(vids, txts, links):
with td(style="word-wrap: break-word;",
halign="center",
valign="top"):
with p():
with a(href=os.path.join('videos', link)):
with video(style="width:%dpx" % width,
controls=True):
source(src=os.path.join('videos', vid),
type="video/mp4")
br()
p(txt)
def index():
removed = list((REPORTS_PATH / "removed").iterdir())
added = list((REPORTS_PATH / "added").iterdir())
diff = list((REPORTS_PATH / "diff").iterdir())
title = "UI changes from master"
doc = dominate.document(title=title)
with doc:
h1("UI changes from master")
hr()
h2("Removed:", style="color: red;")
i("UI fixtures that have been removed:")
html.report_links(removed, REPORTS_PATH)
br()
hr()
h2("Added:", style="color: green;")
i("UI fixtures that have been added:")
html.report_links(added, REPORTS_PATH)
br()
hr()
h2("Differs:", style="color: grey;")
i("UI fixtures that have been modified:")
html.report_links(diff, REPORTS_PATH)
return html.write(REPORTS_PATH, doc, "index.html")
def add_br(self, *args):
if not self.paragraph:
if self.div_subheader:
self.div_subheader.add(tags.br())
elif self.div_header:
self.div_header.add(tags.br())
else:
self.body.add(tags.br())
else:
self.paragraph.add(tags.br())
def html(self, root_dir):
self.save(root_dir)
with p():
with a(href=self.relative_save_path):
img_style = "image-rendering:pixelated;"
if self.display_height is not None:
img_style += 'height:{}px;'.format(self.display_height)
img(style=img_style, src=self.relative_save_path)
if self.desc is not None:
br()
pre(self.desc)
def add_images(self, ims, txts, links, width=400, height=300):
self.add_table()
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word; height:{}px; width:{}px".format(height + 10,width + 10), halign="center", valign="top"):
with p():
with a(href=os.path.join('/',link)):
img(style="width:{}px;height:{}".format(width, height), src=os.path.join('/',im))
br()
p(txt)
def add_images(self, ims, txts, links, width=400):
self.add_table()
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;", halign="center", valign="top"):
with p():
with a(href=os.path.join('images', link)):
img(style="width:%dpx" % width, src=os.path.join('images', im))
br()
p(txt)
def add_images(self, ims, txts, links, width=400):
self.t = table(border=1, style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;", halign="center", valign="top"):
with p():
with a(href=os.path.join('images', link)):
img(style="width:%dpx" % width, src=os.path.join('images', im))
br()
p(txt)
def add(self, columns, no_tqdm=False, display=False):
if display: no_tqdm = True
for i in tqdm(range(0, len(columns), self.ncols), disable=no_tqdm):
T = self.html.add_table(transpose=True)
if self.header: T.set_header(**self.header)
for column in columns[i : min(i + self.ncols, len(columns))]:
T.add_col(**column)
if display:
display_html(T)
with self.html.doc:
br()
return self
def add_footnote_to_output(paragraphs):
with tags.li():
for (para) in paragraphs:
for (run) in para.runs:
style = footer.get_style(run)
if style == "bolded":
with tags.span(run.text):
tags.attr(cls="sub-subject_small")
else:
with tags.span(run.text):
tags.attr(cls="definition_small")
tags.br()
def _add_shopping_links(container, record):
s = t.div(t.a(t.img(src=_lurl(record['resource_source_logo'])),
href=record['url'],
target='_blank'),
cls='shopping_links')
if record['instance_note']:
s += '(' + record['instance_note'] + ')'
container += t.br()
container += s
container += t.br()
else:
container += s
def add_summary(self, dict_):
""" Add a summary with key value pairs from the dictionary """
self.doc += br()
self.doc += hr()
self.doc += br()
self.add_header("Test Summary")
self.doc += br()
for k, v in dict_.items():
self.doc += p(b(k), ' = ', str(v))
self.doc += br()
def add_verbatim_begin(self, *args):
self.add_paragraph()
first_time = True
while True:
if first_time:
self.paragraph.add(tags.br())
first_time = False
next_line = next(self.iterator)
if next_line.startswith('.Ve'):
break
if not self.process_line(next_line):
self.add_roman(next_line)
self.paragraph.add(tags.br())
def build_html(parsed_tokens, css_style):
with document(title="Code") as doc:
style(css_style)
for token in parsed_tokens:
if token.type == line_break:
br()
else:
lines = token.content.split('\n')
for j in range(len(lines)):
if j != 0:
br()
span(lines[j], cls=token.type)
return doc.render(pretty=False)
def add_images(self, ims, txts, links, width=400):
"""Add images to table."""
table = self.add_table()
tr = table.add(htags.tr())
with tr:
for im, txt, link in zip(ims, txts, links):
with htags.td(style="word-wrap: break-word;",
halign="center",
valign="top"):
with htags.p():
with htags.a(href=os.path.join('images', link)):
htags.img(style="width:%dpx" % width,
src=os.path.join('images', im))
htags.br()
htags.p(txt)
def add_images_filterchart(self, ims, txts, links, width=400):
self.add_table()
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;",
halign="center",
valign="top"):
with p():
with a(href=link):
img(style="width:%dpx" % width, src=link)
br()
splitted = txt.split('separator')
if len(splitted) > 1:
for h in splitted:
p(h)
else:
p(txt)
def add_text(self, value):
# FIXME(zpzhou): ugly! remove this hack when have time.
re_full = r'(<span style="color:.*">.*</span>)'
re_part = r'<span style="color:(.*)">(.*)</span>'
value = str(value)
with p(style="line-height: 1.0; font-family: monospace"):
for line in value.split('\n'):
for part in re.split(re_full, line):
found = re.findall(re_part, part)
if found:
color, txt = found[0]
if color == 'red': color = '#DC6A73'
if color == 'green': color = '#88AE6D'
if color == 'yellow': color = '#E4CA6B'
span(txt, style=f'color:{color}')
else:
text(part)
br()
def create_html_news_entry(news, doc_html, internet):
"""Create html for news entry"""
images_links = news.links[1]
all_links = news.create_list_of_links()
with doc_html:
tag.h1(news.title)
with tag.p(news.date):
tag.br()
tag.a("Link to this article", href=news.link)
if internet:
for link in images_links:
tag.img(src=link)
else:
for link in images_links:
tag.a("Image link", href=link)
tag.p(news.text)
for num, link in enumerate(all_links):
tag.a("Link №{}".format(num + 1), href=link)
tag.br()
return doc_html
def show_hide_div(divname: str, hide=False):
"""
Creates a show/hide button and matching div block
:param divname: unique name of the div block
:param hide: the div block is hidden by default if True
:return: the div block
"""
if hide:
hidden.append(divname)
else:
shown.append(divname)
tags.button("Show / Hide",
onclick="hideButton('" + divname + "')")
tags.br()
if hide:
return tags.div(id=divname, style="display:none")
return tags.div(id=divname)
def add_images(self, ims, txts, links, width=400):
"""add images to the HTML file
Parameters:
ims (str list) -- a list of image paths
txts (str list) -- a list of image names shown on the website
links (str list) -- a list of hyperref links; when you click an image, it will redirect you to a new page
"""
from dominate.tags import meta, h3, table, tr, td, p, a, img, br
self.t = table(border=1, style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;", halign="center", valign="top"):
with p():
with a(href=link):
img(style="width:%dpx" % width, src=im)
br()
p(txt)
def deal_with_newlines(text):
''' Add a line break for newline characters. '''
if "\n" not in text:
return text
else:
chunks = [dt.span(t) for t in text.split("\n")]
tag_list = []
for i, chunk in enumerate(chunks):
tag_list.append(chunk)
if i != len(chunks) - 1:
tag_list.append(dt.br())
return tag_list
def create_html_news_entry_for_epub(news, doc_html, internet, list_of_image_objects):
"""Create html for epub news entry"""
images_links = news.links[1]
all_links = news.create_list_of_links()
with doc_html:
tag.h1(news.title)
with tag.p(news.date):
tag.br()
tag.a("Link to this article", href=news.link)
if internet:
for image_object in list_of_image_objects:
tag.img(src=image_object.file_name)
else:
for link in images_links:
if link:
tag.a("Image link", href=link)
tag.p(news.text)
for num, link in enumerate(all_links):
tag.a(f"Link №{num+1}", href=link)
tag.br()
return doc_html
def add_videos(self, vids, txts, links, width=400, hidden_tag="hidden"):
"""add images to the HTML file
Parameters:
vids (str list) -- a list of image paths
txts (str list) -- a list of image names shown on the website
links (str list) -- a list of hyperref links; when you click an image,
it will redirect you to a new page
"""
self.t = table(border=1, style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
colors = ["red", "blue", "gold", "salman"]
with self.t:
with tr():
for vid, txt, link in zip(vids, txts, links):
td_style = "word-wrap: break-word; width:{}px".format(width)
with td(style=td_style, halign="center", valign="top"):
with p():
vid_path = str(vid)
if vid_path == hidden_tag:
p_style = "font-weight: bold; width:{}px;"
p_style = p_style.format(width * 3)
p("hidden video", style=p_style)
else:
with a(href=str(link)):
with video():
attr(controls="controls")
source(src=vid_path, type="video/mp4")
br()
rows = txt.split("<br>")
for idx, row in enumerate(rows):
color = colors[idx % len(colors)]
bold_tag = "<b>"
if not row.startswith(bold_tag):
s_style = "color:{};".format(color)
else:
s_style = "color:black; font-weight: bold;"
row = row[len(bold_tag):]
span(row, style=s_style)
def save_feed_to_html(self):
"""Creating an html file, using curent datetime as a filename"""
logging.info('Started saving feed to html file')
time_now = str(datetime.datetime.now())
time_for_path = time_now[:-16] + '_' + time_now[
-15:-13] + '-' + time_now[-12:-10] + '-' + time_now[-9:-7]
html = dominate.document(title="HTML RSS feed")
with html.head:
dtags.meta(charset='utf-8')
html += dtags.h1(self.feed_name)
for article_number, article in enumerate(self.articles):
html += dtags.br()
date = article.published
str_date = f'{date.tm_year}/{date.tm_mon}/{date.tm_mday} {date.tm_hour}:{date.tm_min}'
html += dtags.h2(f'{article_number + 1}. {article.title}')
html += dtags.h3(f' {str_date}')
html += dtags.a(f'Link: {article.link}')
html += dtags.br()
with html:
if check.internet_connection_check():
# if have internet access, downloading images and pasting in a html file
for link in article.media:
dtags.img(src=link['url'])
else:
# if no, paste links of these images
dtags.a('Image links:')
for link_number, link in enumerate(article.media):
img_url = link['url']
dtags.a(f'{link_number + 1}. {img_url}', href=link)
html += dtags.p(article.summary)
html += dtags.br()
with open('html_feeds/' + time_for_path + ' RSS_feeds.html',
'w') as html_file:
html_file.write(str(html))
logging.info('Finished saving feed to html file')
def __init__(self, *args, field=None, **kwargs):
self.kclass_dep = KClassDep('form-group')
if field is not None:
if field.errors:
self.kclass_dep.append('has-error')
if field.flags.required:
self.kclass_dep.append('required')
super().__init__(**self.update_kwargs(kwargs))
if field is not None:
self.add(
raw(str(field.label)),
br(),
raw(field(class_='form-control')),
)
if field.errors:
for error in field.errors:
self.add(p(error, _class='help-block'))
def hocr(records, image_name=u'', image_size=(0, 0), line_bbox=True,
split_words=True, word_bbox=True, char_cuts=True,
confidence_vals=True):
"""
Merges a list of predictions and their corresponding character positions
into an hOCR document.
Args:
records (iterable): List of kraken.rpred.ocr_record
image_name (unicode): Name of the source image
image_size (tuple): Dimensions of the source image
line_bbox (bool): Enable writing of line bounding boxes
split_words (bool): Split recognized line into words at
non-alphanumeric characters
word_bbox (bool): Enable writing of word bounding boxes (only with
split_words)
char_cuts (bool): Enable writing of character cuts (only with
line_bbox)
confidence_vals (bool): Enable writing of confidence values for
recognition results
"""
doc = dominate.document()
with doc.head:
meta(name='ocr-system', content='kraken')
meta(name='ocr-capabilities', content='ocr_page ocr_line ocrx_word')
meta(charset='utf-8')
with doc:
hocr_title = micro_hocr()
if image_size > (1, 1):
hocr_title.add('bbox', 0, 0, *[str(s) for s in image_size])
if image_name:
hocr_title.add(u'image', image_name)
with div(cls='ocr_page', title=str(hocr_title)):
for idx, record in enumerate(records):
logger.debug('Adding record {} - {} to hocr'.format(idx, record.prediction))
with span(cls='ocr_line', id='line_' + str(idx)) as line_span:
line_title = micro_hocr()
if line_bbox:
line_title.add('bbox', *max_bbox(record.cuts))
if char_cuts:
line_title.add('cuts',
*list(delta(max_bbox(record.cuts),
record.cuts)))
# only add if field contains text to avoid unseemly empty
# titles
if str(line_title):
line_span['title'] = str(line_title)
if split_words:
logger.debug('Splitting record into words')
splits = regex.split(u'(\w+)', record.prediction)
line_offset = 0
# operate on pairs of non-word character strings and
# words. The former are encoded in ocrx_cinfo classes
# while the latter is adorned with ocrx_word classes.
for w_idx, non_word, word in zip(count(), splits[0::2],
splits[1::2]):
# add non word blocks only if they contain actual
# text
if non_word:
nw_span = span(non_word, cls='ocrx_block',
id='block_' + str(idx) + '_' +
str(w_idx))
nw = micro_hocr()
if word_bbox:
nw.add('bbox',
*max_bbox(record.cuts[line_offset:line_offset
+
len(non_word)]))
if confidence_vals:
nw.add('x_conf', *[str(int(100*v)) for v in
record.confidences[line_offset:line_offset
+
len(non_word)]])
if str(nw):
nw_span['title'] = str(nw)
line_offset += len(non_word)
w_span = span(word, cls='ocrx_word', id='word_' +
str(idx) + '_' + str(w_idx))
w = micro_hocr()
if word_bbox:
w.add('bbox',
*max_bbox(record.cuts[line_offset:line_offset
+ len(word)]))
if confidence_vals:
w.add('x_conf', *[str(int(100*v)) for v in
record.confidences[line_offset:line_offset
+
len(word)]])
if str(w):
w_span['title'] = str(w)
line_offset += len(word)
else:
line_span.add(record.prediction)
br()
return doc