def _path(self, node): self.path = self.canvas.beginPath() self.path.moveTo(**utils.getAttrsAsDict(node, ['x', 'y'])) for n in node.childNodes: if n.nodeType == node.ELEMENT_NODE: if n.localName=='moveto': vals = utils.getText(n).split() self.path.moveTo(utils.as_pt(vals[0]), utils.as_pt(vals[1])) elif n.localName=='curvesto': vals = utils.getText(n).split() while len(vals)>5: pos=[] while len(pos)<6: pos.append(utils.as_pt(vals.pop(0))) self.path.curveTo(*pos) elif (n.nodeType == node.TEXT_NODE): data = n.data.split() # Not sure if I must merge all TEXT_NODE ? while len(data)>1: x = utils.as_pt(data.pop(0)) y = utils.as_pt(data.pop(0)) self.path.lineTo(x, y) if ((not node.hasAttribute('close')) or utils.as_bool(node.getAttribute('close'))): self.path.close() self.canvas.drawPath( self.path, **utils.getAttrsAsDict(node, [], {'fill':'bool','stroke':'bool'}))
def find_episodes(params): import xml.dom.minidom baseurl = 'http://www.uitzendinggemist.nl' url = urllib.unquote(params['url']) module = params['module'] page = "" pagecount = 1 while pagecount<10: rssurl = baseurl + url + '.rss?page=' + str(pagecount) request = common.fetchPage({"link": rssurl, "cookie": "site_cookie_consent=yes"}) if not request["status"] == 200: break page = request["content"].encode('utf-8') try: dom = xml.dom.minidom.parseString(page) except: page = page.replace("&","&") dom = xml.dom.minidom.parseString(page) if len(dom.getElementsByTagName('item'))==0: break else: for item in dom.getElementsByTagName('item'): videourl = utils.getText(item.getElementsByTagName('link')[0].childNodes) videourl = urllib.quote_plus(videourl) videourl = sys.argv[0]+"?module="+module+"&action=find_video"+"&url="+videourl try: thumb = item.getElementsByTagName('media:thumbnail')[0].attributes['url'].value except: thumb = "" title = common.replaceHTMLCodes(utils.getText(item.getElementsByTagName('title')[0].childNodes)) utils.addLink(title, videourl, thumb) pagecount = pagecount+1 xbmcplugin.endOfDirectory(int(sys.argv[1]))
def _lines(self, node): line_str = utils.getText(node).split() lines = [] while len(line_str)>3: lines.append([utils.as_pt(l) for l in line_str[0:4]]) line_str = line_str[4:] self.canvas.lines(lines)
def predict(filename): raw_text = getText(filename) data = getDataset(raw_text) model = defineModel(data) loadWeights(model) generateText(model, raw_text)
def main(planet=None, lang=None, layout=None): templateLoader = jinja2.FileSystemLoader(searchpath='print/templates/') templateEnv = jinja2.Environment(loader=templateLoader) planets = [ 'mercury', 'venus', 'earth', 'mars', 'jupiter', 'saturn', 'uranus', 'neptune', ] if planet is not None: data = [getJson('data/planets/'+planet+'.json')] else: data = [getJson('data/planets/'+planet+'.json') for planet in planets] if lang is None: lang = ['fr', 'en'] else: lang = [lang] cssPages = getText('print/stylesheet.css') cssInt = getText('print/stylesheet-intercalar.css') for planetData in data: catalog = Pages(planetData) intercalar = Intercalar(planetData) cribsheet = CribSheet(planetData) for l in lang: pages = catalog.generate(templateEnv, cssPages, l, layout) intercalars = intercalar.generate(templateEnv, cssInt, l, layout) cribsheetRender = cribsheet.generate(templateEnv, cssInt, l, None) print('Saving ' + planetData['name']['en'] + '' + l) if layout is None: pages = intercalars + pages saveAsPDF(pages, planetData['name']['en'] + '-' + l, folder='output/print/preview/') saveAsPDF(cribsheetRender, planetData['name']['en']+ '-cribsheet-' + l, folder='output/print/preview/') else: saveAsPDF(pages, planetData['name']['en'] + '-' + l) saveAsPDF(intercalars, planetData['name']['en'] + '-' + l, folder='output/print/intercalars/') saveAsPDF(cribsheetRender, planetData['name']['en']+ '-cribsheet-' + l) print('Done !\n\n\n')
def train(filename): raw_text = getText(filename) data = getDataset(raw_text) model = defineModel(data) fitModel(model, data)
moby = set([line.rstrip() for line in open(moby_file, encoding='mac_roman')]) # print(len(moby)) print('Building dicts...') word_indices = dict((line.split('*')[0], (i, line.split('*')[1])) for i, line in enumerate(moby)) indices_word = dict((i, line.split('*')[0]) for i, line, in enumerate(moby)) parts = set([pos for line in moby for pos in line.split('*')[1]]) pos_indices = dict((pos, i) for i, pos in enumerate(parts)) indices_pos = dict((i, pos) for i, pos in enumerate(parts)) texts = [] texts.append([s for s in getText(0) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(1) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(2) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(3) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(4) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(5) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(6) if isAdmissible(s, word_indices)]) # for text in texts: # print(len(text)) maxlen = 128 def TrainPosModel(model, dimIn, dimOut): print('Generating training set...')
def _curves(self, node): line_str = utils.getText(node).split() lines = [] while len(line_str)>7: self.canvas.bezier(*[utils.as_pt(l) for l in line_str[0:8]]) line_str = line_str[8:]
def main(data): ## Loop through languages trPath = os.path.join( data["definitions"]["runtime"]["cwd"], data["config"]["Filesystem"]["SourcePathTranslations"], ) trPath = os.path.abspath(trPath) languages = sorted(next(os.walk(trPath))[1]) for languageKey in languages: data["translations"][languageKey] = {} trLanguagePath = os.path.join( trPath, languageKey, ) ## Loop through artist groups groups = sorted(next(os.walk(trLanguagePath))[1]) for groupKey in groups: data["translations"][languageKey][groupKey] = {} trLanguageGroupPath = os.path.join( trLanguagePath, groupKey, ) ## Loop through artists start begin with artists = sorted(next(os.walk(trLanguageGroupPath))[1], key=str.lower) for artistKey in artists: trLanguageGroupArtistPath = os.path.join( trLanguageGroupPath, artistKey, ) data["translations"][languageKey][groupKey][artistKey] = { "printable_name": artistKey, "releases": [], } ## Loop through artist’s releases releases = sorted(next(os.walk(trLanguageGroupArtistPath))[1], key=str.lower) for releaseKey in releases: trLanguageGroupArtistReleasePath = os.path.join( trLanguageGroupArtistPath, releaseKey, ) data["translations"][languageKey][groupKey][artistKey][ "releases"].append({ "name": releaseKey, "printable_name": releaseKey, "recordings": [[]], }) ## Loop through release’s recordings recordings = sorted(next( os.walk(trLanguageGroupArtistReleasePath))[2], key=str.lower) for recordingKey in recordings: trLanguageGroupArtistReleaseRecordingPath = os.path.join( trLanguageGroupArtistReleasePath, recordingKey, ) rawContents = open( trLanguageGroupArtistReleaseRecordingPath, "r").read().strip() rawText = utils.getText(rawContents) rawMetadata = utils.getMetadata(rawContents) data["translations"][languageKey][groupKey][artistKey][ "releases"][-1]["recordings"][0].append({ "name": recordingKey, "printable_name": recordingKey, "text": rawText, "metadata": utils.parseMetadata(rawMetadata), })
moby_file = os.path.join(root, 'mpos', 'mobyposi - Copy.i') moby = set([line.rstrip() for line in open(moby_file, encoding = 'mac_roman')]) # print(len(moby)) print('Building dicts...') word_indices = dict((line.split('*')[0], (i, line.split('*')[1])) for i,line in enumerate(moby)) indices_word = dict((i, line.split('*')[0]) for i,line, in enumerate(moby)) parts = set([pos for line in moby for pos in line.split('*')[1]]) pos_indices = dict((pos, i) for i,pos in enumerate(parts)) indices_pos = dict((i, pos) for i,pos in enumerate(parts)) texts = [] texts.append([s for s in getText(0) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(1) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(2) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(3) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(4) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(5) if isAdmissible(s, word_indices)]) texts.append([s for s in getText(6) if isAdmissible(s, word_indices)]) # for text in texts: # print(len(text)) maxlen = 128 def TrainPosModel(model, dimIn, dimOut): print('Generating training set...') text = [w for s in texts[0] for w in s]+\
url = 'http://%s:%s/entity/search?q={"limit":%d,"cursor":%s}&opts=%s' % ( httpConfig.config["serverhost"], httpConfig.config["serverport"], limit, json.dumps(cursor), json.dumps(opts), ) print ("doGet: url = %s" % url) r = requests.get(url) statusCode = r.status_code try: utils.getJson(r) except Exception(e): print utils.getText(r) continue cursor = j["cursor"] status = j["status"] print ("doGet: Got %d results" % len(j["response"])) for item in j["response"]: itemId = item["props"]["urn:lri:property_type:id"] # XXX: should this be: if item in items? if item in items: print ("doGet: DUPLICATE: %s" % itemId) else: items.append(item) count += 1 print ("doGet: Got %d items: " % len(items))