def get_context_data(self, *args, **kwargs):
context = super(MeetingDetailView, self).get_context_data(*args, **kwargs)
cm = context['object']
colors = {}
speakers = cm.parts.order_by('speaker__mk').values_list('header','speaker__mk').distinct()
n = speakers.count()
for (i,(p,mk)) in enumerate(speakers):
(r,g,b) = colorsys.hsv_to_rgb(float(i)/n, 0.5 if mk else 0.3, 255)
colors[p] = 'rgb(%i, %i, %i)' % (r, g, b)
context['title'] = _('%(committee)s meeting on %(date)s') % {'committee':cm.committee.name, 'date':cm.date_string}
context['description'] = _('%(committee)s meeting on %(date)s on topic %(topic)s') \
% {'committee':cm.committee.name,
'date':cm.date_string,
'topic':cm.topics}
context['description'] = clean_string(context['description']).replace('"', '')
page = self.request.GET.get('page', None)
if page:
context['description'] += _(' page %(page)s') % {'page': page}
context['colors'] = colors
parts_lengths = {}
for part in cm.parts.all():
parts_lengths[part.id] = len(part.body)
context['parts_lengths'] = json.dumps(parts_lengths)
context['paginate_by'] = models.COMMITTEE_PROTOCOL_PAGINATE_BY
if cm.committee.type == 'plenum':
context['members'] = cm.mks_attended.order_by('name')
context['hide_member_presence'] = True
else:
#get meeting members with presence calculation
meeting_members_ids = set(m.id for m in cm.mks_attended.all())
context['members'] = cm.committee.members_by_presence(ids=meeting_members_ids)
context['hide_member_presence'] = False
return context
def parse_pdf_text(filename=None, url=None):
logger.debug('parse_pdf_text filename=%s url=%s' %
(str(filename), str(url)))
if not filename:
filename = 'tmp.txt'
f = open(filename, 'rt')
content = f.read()
d = None
result = []
m = re.search('עמוד(.*?)מתפרסמת בזה', content, re.UNICODE | re.DOTALL)
if not m: # couldn't read this file
logger.warn("can't read this file")
return None
m = clean_string(m.group(1).decode('utf8'))
m2 = re.findall('^(הצעת חוק.*?) \. '.decode('utf8'), m,
re.UNICODE | re.DOTALL | re.MULTILINE)
m3 = re.findall('^(חוק.*?) \. '.decode('utf8'), m,
re.UNICODE | re.DOTALL | re.MULTILINE)
m2.extend(m3)
for title in m2:
law = {}
title = title.replace('\n', ' ')
s = re.search(r'[^\d]\d{2,3}[^\d]', title + ' ',
re.UNICODE) # find numbers of 2-3 digits
if s:
(a, b) = s.span()
title = title[:a + 1] + title[b -
2:a:-1] + title[b -
1:] # reverse them
law['title'] = title
result.append(law)
count = 0 # count how many bills we found the original_ids for so far
lines = content.split('\n')
for line in lines:
m = re.search('(\d{4,4})[\.|\s](\d+)[\.|\s](\d+)', line)
if m:
d = date(int(m.group(1)[::-1]), int(m.group(2)[::-1]),
int(m.group(3)[::-1]))
m = re.search(
'[הצעת|הצעות] חוק מס.*?\d+/\d+.*?[הועברה|הועברו]'.decode('utf8'),
line.decode('utf8'), re.UNICODE)
if m:
try:
result[count]['references'] = line
m2 = re.findall('\d+/\d+', line.decode('utf8'),
re.UNICODE) # find IDs of original proposals
result[count]['original_ids'] = [a[::-1] for a in m2]
count += 1
except IndexError:
logger.exception(
u'parse knesset pdf exception with content {0}'.format(
content))
for l in result:
l['date'] = d
return result
def parse_pdf_text(filename=None, url=None):
logger.debug("parse_pdf_text filename=%s url=%s" % (str(filename), str(url)))
if not filename:
filename = "tmp.txt"
f = open(filename, "rt")
content = f.read()
d = None
result = []
m = re.search("עמוד(.*?)מתפרסמת בזה", content, re.UNICODE | re.DOTALL)
if not m: # couldn't read this file
logger.warn("can't read this file")
return None
m = clean_string(m.group(1).decode("utf8"))
m2 = re.findall("^(הצעת חוק.*?) \. ".decode("utf8"), m, re.UNICODE | re.DOTALL | re.MULTILINE)
m3 = re.findall("^(חוק.*?) \. ".decode("utf8"), m, re.UNICODE | re.DOTALL | re.MULTILINE)
m2.extend(m3)
for title in m2:
law = {}
title = title.replace("\n", " ")
s = re.search(r"[^\d]\d{2,3}[^\d]", title + " ", re.UNICODE) # find numbers of 2-3 digits
if s:
(a, b) = s.span()
title = title[: a + 1] + title[b - 2 : a : -1] + title[b - 1 :] # reverse them
law["title"] = title
result.append(law)
count = 0 # count how many bills we found the original_ids for so far
lines = content.split("\n")
for line in lines:
m = re.search("(\d{4,4})[\.|\s](\d+)[\.|\s](\d+)", line)
if m:
d = date(int(m.group(1)[::-1]), int(m.group(2)[::-1]), int(m.group(3)[::-1]))
m = re.search("הצעת חוק מס.*?\w+/\d+/\d+.*?[הועברה|הועברו]".decode("utf8"), line.decode("utf8"), re.UNICODE)
if m:
try:
result[count]["references"] = line
m2 = re.findall("\w+/\d+/\d+", line.decode("utf8"), re.UNICODE) # find IDs of original proposals
result[count]["original_ids"] = [a[-1:0:-1] + a[0] for a in m2] # reverse
count += 1
except IndexError:
exceptionType, exceptionValue, exceptionTraceback = sys.exc_info()
logger.error(
"%s", "".join(traceback.format_exception(exceptionType, exceptionValue, exceptionTraceback))
)
logger.error(
"count=%d, len(result)=%d, content = \n%s\n--- end of content"
% (count, len(result), content.decode("utf8"))
)
for l in result:
l["date"] = d
return result
def parse_pdf_text(filename=None, url=None):
logger.debug('parse_pdf_text filename=%s url=%s' % (str(filename),
str(url)))
if not filename:
filename = 'tmp.txt'
f = open(filename,'rt')
content = f.read()
d = None
result = []
m = re.search('עמוד(.*?)מתפרסמת בזה',content, re.UNICODE | re.DOTALL)
if not m: # couldn't read this file
logger.warn("can't read this file")
return None
m = clean_string(m.group(1).decode('utf8'))
m2 = re.findall('^(הצעת חוק.*?) \. '.decode('utf8'), m, re.UNICODE | re.DOTALL | re.MULTILINE)
m3 = re.findall('^(חוק.*?) \. '.decode('utf8'),m, re.UNICODE | re.DOTALL | re.MULTILINE)
m2.extend(m3)
for title in m2:
law = {}
title = title.replace('\n',' ')
s = re.search(r'[^\d]\d{2,3}[^\d]',title+' ',re.UNICODE) # find numbers of 2-3 digits
if s:
(a,b) = s.span()
title = title[:a+1] + title[b-2:a:-1] + title[b-1:] # reverse them
law['title'] = title
result.append(law)
count = 0 # count how many bills we found the original_ids for so far
lines = content.split('\n')
for line in lines:
m = re.search('(\d{4,4})[\.|\s](\d+)[\.|\s](\d+)', line)
if m:
d = date(int(m.group(1)[::-1]), int(m.group(2)[::-1]), int(m.group(3)[::-1]))
m = re.search('[הצעת|הצעות] חוק מס.*?\d+/\d+.*?[הועברה|הועברו]'.decode('utf8'), line.decode('utf8'), re.UNICODE)
if m:
try:
result[count]['references'] = line
m2 = re.findall('\d+/\d+',line.decode('utf8'), re.UNICODE) # find IDs of original proposals
result[count]['original_ids'] = [a[::-1] for a in m2]
count += 1
except IndexError:
exceptionType, exceptionValue, exceptionTraceback = sys.exc_info()
logger.error("%s", ''.join(traceback.format_exception(exceptionType, exceptionValue, exceptionTraceback)))
logger.error('count=%d, len(result)=%d, content = \n%s\n--- end of content' % \
(count, len(result), content.decode('utf8')))
for l in result:
l['date'] = d
return result
def parse_pdf_text(filename=None, url=None):
if not filename:
filename = 'tmp.txt'
f = open(filename, 'rt')
content = f.read()
d = None
result = []
m = re.search('עמוד(.*?)מתפרסמת בזה', content, re.UNICODE | re.DOTALL)
m = clean_string(m.group(1).decode('utf8'))
m2 = re.findall('^(הצעת חוק.*?) . '.decode('utf8'), m,
re.UNICODE | re.DOTALL | re.MULTILINE)
m3 = re.findall('^(חוק.*?) . '.decode('utf8'), m,
re.UNICODE | re.DOTALL | re.MULTILINE)
m2.extend(m3)
for title in m2:
law = {}
title = title.replace('\n', ' ')
s = re.search(r'[^\d]\d{2,3}[^\d]', title + ' ',
re.UNICODE) # find numbers of 2-3 digits
if s:
(a, b) = s.span()
title = title[:a + 1] + title[b -
2:a:-1] + title[b -
1:] # reverse them
law['title'] = title
result.append(law)
count = 0 # count how many bills we found the original_ids for so far
lines = content.split('\n')
for line in lines:
m = re.search('(\d{4,4})[\.|\s](\d+)[\.|\s](\d+)', line)
if m:
d = date(int(m.group(1)[::-1]), int(m.group(2)[::-1]),
int(m.group(3)[::-1]))
m = re.search(
'הצעת חוק מס.*?\w+/\d+/\d+.*?[הועברה|הועברו]'.decode('utf8'),
line.decode('utf8'), re.UNICODE)
if m:
result[count]['references'] = line
m2 = re.findall('\w+/\d+/\d+', line.decode('utf8'),
re.UNICODE) # find IDs of original proposals
result[count]['original_ids'] = [a[-1:0:-1] + a[0]
for a in m2] # reverse
count += 1
for l in result:
l['date'] = d
return result
def parse_pdf_text(filename=None, url=None):
if not filename:
filename = 'tmp.txt'
f = open(filename,'rt')
content = f.read()
d = None
result = []
m = re.search('עמוד(.*?)מתפרסמת בזה',content, re.UNICODE | re.DOTALL)
m = clean_string(m.group(1).decode('utf8'))
m2 = re.findall('^(הצעת חוק.*?) . '.decode('utf8'), m, re.UNICODE | re.DOTALL | re.MULTILINE)
m3 = re.findall('^(חוק.*?) . '.decode('utf8'),m, re.UNICODE | re.DOTALL | re.MULTILINE)
m2.extend(m3)
for title in m2:
law = {}
title = title.replace('\n',' ')
s = re.search(r'[^\d]\d{2,3}[^\d]',title+' ',re.UNICODE) # find numbers of 2-3 digits
if s:
(a,b) = s.span()
title = title[:a+1] + title[b-2:a:-1] + title[b-1:] # reverse them
law['title'] = title
result.append(law)
count = 0 # count how many bills we found the original_ids for so far
lines = content.split('\n')
for line in lines:
m = re.search('(\d{4,4})[\.|\s](\d+)[\.|\s](\d+)', line)
if m:
d = date(int(m.group(1)[::-1]), int(m.group(2)[::-1]), int(m.group(3)[::-1]))
m = re.search('הצעת חוק מס.*?\w+/\d+/\d+.*?[הועברה|הועברו]'.decode('utf8'), line.decode('utf8'), re.UNICODE)
if m:
result[count]['references'] = line
m2 = re.findall('\w+/\d+/\d+',line.decode('utf8'), re.UNICODE) # find IDs of original proposals
result[count]['original_ids'] = [a[-1:0:-1]+a[0] for a in m2] # reverse
count += 1
for l in result:
l['date'] = d
return result
def get_context_data(self, *args, **kwargs):
context = super(MeetingDetailView, self).get_context_data(*args, **kwargs)
meeting = context["object"]
transcript = meeting.transcript
colors = {}
speakers = transcript.blocks.order_by("speaker__mk").values_list("header", "speaker__mk").distinct()
n = speakers.count()
for (i, (p, mk)) in enumerate(speakers):
(r, g, b) = colorsys.hsv_to_rgb(float(i) / n, 0.5 if mk else 0.3, 255)
colors[p] = "rgb(%i, %i, %i)" % (r, g, b)
context["title"] = _("Plenum meeting on %(date)s") % {"date": meeting.date}
context["description"] = meeting.title
context["description"] = clean_string(context["description"]).replace('"', "")
page = self.request.GET.get("page", None)
if page:
context["description"] += _(" page %(page)s") % {"page": page}
context["colors"] = colors
parts_lengths = {}
for block in transcript.blocks.all():
parts_lengths[block.id] = len(block.body)
context["parts_lengths"] = json.dumps(parts_lengths)
context["paginate_by"] = TRANSCRIPT_PAGINATE_BY
return context
