Python ElementTree.parse方法代码示例

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		with open(path, "r") as f:
			root = ElementTree.parse(f).getroot()

		list = {
			"items": [],
		}

		for i, itemTree in enumerate(root.findall("Vokabeldatensatz/Datensatz")):
			word = {
				"id": i,
				"questions": [],
				"answers": [],
			}
			comments = []
			for question in itemTree.findall("Vokabeln/string"):
				word["questions"].append((question.text,))
			for answer in itemTree.findall("Vokabeln/string"):
				word["answers"].append((answer.text,))
			for comment in itemTree.findall("Kommentare/string"):
				comments.append((comment.text))
			if comments:
				word["comment"] = u"; ".join(comments)

			list["items"].append(word)

		return {
			"resources": {},
			"list": list,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		wsp = self._modules.default("active", type="wordsStringParser")

		with open(path) as f:
			root = ElementTree.parse(f).getroot()

		wordList = {
			"items": [],
		}

		wordList["questionLanguage"] = root.findtext("fields/field[1]") or u""
		wordList["answerLanguage"] = root.findtext("fields/field[2]") or u""

		#counter is used as word id
		counter = itertools.count()

		for entryTree in root.findall("entries/e"):
			wordList["items"].append({
				"id": next(counter),
				"questions": wsp.parse(entryTree.findtext("f[1]") or u""),
				"answers": wsp.parse(entryTree.findtext("f[2]")  or u""),
				"comment": entryTree.findtext("f[3]")  or u"",
			})

		return {
			"resources": {},
			"list": wordList,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		"""Loads .fq (FlashQard) files. Based on file format inspection.
		   (even though source code is available, see
		   http://flashqard-project.org/download.php)

		"""
		with open(path, "r") as f:
			root = ElementTree.parse(f).getroot()

		list = {
			"items": [],
			"title": root.find("box").get("name"),
		}

		for i, itemTree in enumerate(root.findall(".//card")):
			questions = self._stripTags(itemTree.findtext("frontsidedocument/html"))
			answers = self._stripTags(itemTree.findtext("backsidedocument/html"))
			created = itemTree.findtext("statistics/dateCreated")
			list["items"].append({
				"id": i,
				"questions": self._parse(questions),
				"answers": self._parse(answers),
				"comment": self._stripTags(itemTree.findtext("comments")),
				"created": datetime.datetime.strptime(created, "%d.%m.%Y")
			})

		return {
			"resources": {},
			"list": list,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		"""Loads Teachmaster's .vok2 files. Lesson info is stored in
		   additional files, but that's not loaded. It might not map to
		   the OT result system either (not sure). For documentation on
		   the file format in German (translations are available, but
		   those aren't all complete/up-to-date):

		   http://www.teachmaster.de/wikka/DocumentationDEDateiformate

		"""
		with open(path, "r") as f:
			root = ElementTree.parse(f).getroot()

		list = {
			"items": [],
			"title": root.findtext("header/titel") or u"",
			"questionLanguage": root.findtext("header/spreins") or u"",
			"answerLanguage": root.findtext("header/sprzwei"),
		}

		for i, itemTree in enumerate(root.findall("vokabelsatz")):
			word = self._loadWordFromItemTree(itemTree)
			word["id"] = i

			list["items"].append(word)

		return {
			"resources": {},
			"list": list,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		wsp = self._modules.default("active", type="wordsStringParser")

		root = ElementTree.parse(open(path)).getroot()

		wordList = {
			"items": list(),
			"title": root.get("title", u""),
		}

		#a counter is used to suppply the ids. That's because ABBYY
		#Lingvo Tutor decided to not include ids anymore from version X5
		#on.
		counter = itertools.count()

		wordList["items"] = [
			{
				"id": next(counter),
				"questions": wsp.parse(wordTree.findtext("word") or u""),
				"answers": [[a.text or u"" for a in wordTree.findall("meanings/meaning/translations/word")]],
				"commentAfterAnswering": u", ".join(
					e.text or u""
					for e in wordTree.findall("meanings/meaning/examples/example")
				)
			}
			for wordTree in root.findall("card")
		]

		return {
			"resources": {},
			"list": wordList,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		#reference implementation:
		#http://jmemorize.svn.sourceforge.net/viewvc/jmemorize/trunk/jmemorize/src/jmemorize/core/io/XmlBuilder.java?view=markup
		try:
			with contextlib.closing(zipfile.ZipFile(path, "r")) as f:
				xmlFile = f.open("lesson.xml", "r")
		except (zipfile.BadZipfile, KeyError):
			xmlFile = open(path, "r")

		#crashes when the file structure is invalid.
		try:
			root = ElementTree.parse(xmlFile).getroot()
		finally:
			xmlFile.close()
		items = []
		for i, card in enumerate(root.findall(".//Card")):
			item = {
				"id": i,
				"questions": self._parse(card.get("Frontside") or u""),
				"answers": self._parse(card.get("Backside") or u""),
			}
			created = card.get("DateCreated")
			if created:
				item["created"] = self._parseDate(created)
			items.append(item)

		return {
			"resources": {},
			"list": {
				"items": sorted(items, key=lambda item: item.get("created")),
				"tests": [],
			},
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		with open(path) as f:
			root = ElementTree.parse(f).getroot()
		#dutch: lijst = list
		listTree = root.find("lijst")

		wordList = {
			"items": list(),
		}

		#dutch: titel = title
		wordList["title"] = listTree.findtext("titel") or u""
		#dutch: taal = language
		wordList["questionLanguage"] = listTree.findtext("taal/a") or u""
		wordList["answerLanguage"] = listTree.findtext("taal/b") or u""

		#change locale temporary; so strptime can do it's work the way
		#it should.
		locale.setlocale(locale.LC_ALL, "C")
		try:
			created = datetime.datetime.strptime(
				listTree.findtext("created").rsplit(" ", 1)[0], #strip tz info
				"%a, %d %b %Y %H:%M:%S" #since our datetime objects are naive
			)
		except (ValueError, AttributeError):
			created = None
		#set locale back to make sure conflicts don't arise with other
		#modules depending on the locale.
		locale.resetlocale()

		#counter is used as word id
		counter = 1

		#dutch: woord = word
		for wordTree in listTree.findall("woord"):
			word = {
				"id": int(),
				"questions": list(),
				"answers": list(),
				"comment": unicode()
			}
			word["id"] = counter
			if created:
				word["created"] = created

			wsp = self._modules.default("active", type="wordsStringParser")
			word["questions"] = wsp.parse(wordTree.findtext("a") or u"")
			word["answers"] = wsp.parse(wordTree.findtext("b") or u"")

			wordList["items"].append(word)

			counter += 1

		return {
			"resources": {},
			"list": wordList,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def getFileTypeOf(self, path):
		if path.endswith(".t2k"):
			root = ElementTree.parse(open(path)).getroot()
			if root.find("message_data/items//item/answers[@type='4']") is not None:
				return "topo"
			else:
				#also support other formats in the future? Well,
				#everything that's left can be opened like it's of type 'words'...
				return "words"

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		"""Loads a .t2k file into the OpenTeacher data structure.
		   http://www.teach2000.nl/help/00513_advanced_file_format.htm

		"""
		root = ElementTree.parse(open(path)).getroot()
		if self.getFileTypeOf(path) == "topo":
			return self._loadTopo(root)
		else:
			return self._loadWords(root)

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		if path.endswith(".pau"):
			with open(path) as f:
				root = ElementTree.parse(f).getroot()
		else:
			with contextlib.closing(gzip.open(path)) as f:
				root = ElementTree.parse(f).getroot()

		wordList = {
			#only the first line, because a description can be pretty
			#long in Pauker...
			"title": (root.findtext("Description") or u"").split("\n")[0].strip(),
			"items": [],
		}
		cards = root.findall("Batch//Card")
		if cards is not None:
			for id, card in enumerate(cards):
				questions = self._parse(
					(card.findtext("FrontSide") or u"").strip() or
					(card.findtext("FrontSide/Text") or u"").strip() or
					u""
				)
				answers = self._parse(
					(card.findtext("BackSide") or u"").strip() or
					(card.findtext("BackSide/Text") or u"").strip() or
					(card.findtext("ReverseSide") or u"").strip() or
					(card.findtext("ReverseSide/Text") or u"").strip() or
					u""
				)

				wordList["items"].append({
					"id": id,
					"questions": questions,
					"answers": answers
				})

		return {
			"resources": {},
			"list": wordList,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, kgmPath):
		#Feed the xml parser
		with open(kgmPath) as f:
			root = ElementTree.parse(f).getroot()
		#load the map, in various later needed formats
		mapPath = os.path.join(os.path.dirname(kgmPath), root.findtext("mapFile"))
		mapImage = Image.open(mapPath).convert("RGB")
		mapImageData = mapImage.load()

		items = []
		for counter, division in enumerate(root.findall("division")):
			#iterate over all places ('divisions')
			if division.findtext("ignore") == "yes":
				#unimportant division: skip
				continue
			item = {
				"id": counter,
				"name": division.findtext("name") or u"",
			}

			#get the color the place has on the map
			r = int(division.findtext("color/red"))
			g = int(division.findtext("color/green"))
			b = int(division.findtext("color/blue"))
			color = (r, g, b)

			#get the average pixel with that color. This is done by
			#iterating over all pixels and using them to calculate an
			#average if the color matches.
			sumX = 0
			sumY = 0
			count = 0
			for x in range(mapImage.size[0]):
				for y in range(mapImage.size[1]):
					if mapImageData[x, y] == color:
						sumX += x
						sumY += y
						count += 1
			#save the averages as coordinate.
			item["x"] = sumX / count
			item["y"] = sumY / count

			items.append(item)

		return {
			"resources": {
				"mapPath": mapPath,
			},
			"list": {
				"items": items,
			},
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
def image2svg(im_path, embed_image=True):
    ### Only part of the code that uses PIL ######
    im = Image.open(im_path)
    width, height = im.size
    fmt = im.format.lower()
    ### End of PIL ###############################

    if embed_image:
        f = open(im_path, 'rb')
        im_contents = f.read()
        f.close()
        b64 = base64.b64encode(im_contents)
        #im_href = "data:image/" + fmt + ";base64," + base64.b64encode(im_contents)
        im_href = "data:image/{0};base64,{1}".format(fmt, b64)
    else:
        im_href = "file:" + urllib.pathname2url(im_path)

    ### SVG ###
    doc = etree.parse(blank_svg_path)
    svg = doc.getroot()
    svg.set('width', str(width))
    svg.set('height', str(height))
    svg.set('xmlns:xlink', "http://www.w3.org/1999/xlink")
    ### Use descriptive variables for the layers
    image_layer = svg[image_layer_index]
    shapes_layer = svg[shapes_layer_index]
    ### Create the 'image' element
    image = etree.SubElement(image_layer, 'image')
    image.set('x', '0')
    image.set('y', '0')
    image.set('height', str(height))
    image.set('width', str(width))
    image.set('xlink:href', im_href)  # encode base64
    ###
    svg_content = etree.tostring(svg)  # remove
    #### Very Ugly Hack Ahead !!!
    hack_head, hack_body = svg_content.split('\n', 1)
    hack_head = hack_head[:-1]
    hack_head = ''.join([hack_head, ' xmlns="http://www.w3.org/2000/svg">'])
    svg_content = '\n'.join([hack_head, hack_body])
    #### END HACK

    svg_b64 = "data:image/svg+xml;base64," + base64.b64encode(svg_content)

    return {'svg': svg_content,
            'svg_b64': svg_b64,
            'height': height,
            'width': width}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		items = []

		with open(path, "r") as f:
			root = ElementTree.parse(f).getroot()

		for id, card in enumerate(root.findall("card")):
			items.append({
				"id": id,
				"questions": self._parse(card.findtext("front") or u""),
				"answers": self._parse(card.findtext("back") or u""),
			})

		return {
			"list": {
				"items": items,
			},
			"resources": {},
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		"""Documentation: http://jvlt.sourceforge.net/download.html
		   (at the bottom)

		"""
		with contextlib.closing(zipfile.ZipFile(path)) as jvltZip:
			root = ElementTree.parse(jvltZip.open("dict.xml")).getroot()

		list = {"items": []}

		for i, itemTree in enumerate(root.findall(".//entry")):
			list["items"].append({
				"id": i,
				"questions": self._parse(itemTree.findtext("orth") or u""),
				"answers": self._parse(itemTree.findtext("sense/trans") or u""),
				"comment": u", ".join([pron.text for pron in itemTree.findall("pron")]),
			})

		return {
			"resources": {},
			"list": list,
		}

# 需要导入模块: from etree import ElementTree [as 别名]
# 或者: from etree.ElementTree import parse [as 别名]
	def load(self, path):
		"""Tries to load .wcu CueCard files. Based on observation of the
		   file format, not on documentation. Seems like there is source
		   code available though.

		"""
		with open(path, "r") as f:
			root = ElementTree.parse(f).getroot()

		items = []
		for id, card in enumerate(root.findall("Card")):
			items.append({
				"id": id,
				"questions": self._parse(card.get("Question")),
				"answers": self._parse(card.get("Answer")),
			})

		return {
			"list": {
				"items": items,
			},
			"resources": {},
		}