def performOPFSourceUpdates(data, currentdir, keylist, valuelist):
# rebuild serialized lookup dictionary
updates = {}
for i in range(0, len(keylist)):
updates[ keylist[i] ] = valuelist[i]
xmlbuilder = LXMLTreeBuilderForXML(parser=None, empty_element_tags=ebook_xml_empty_tags)
soup = BeautifulSoup(data, features=None, builder=xmlbuilder)
for tag in soup.find_all(["item","reference","site"]):
if "href" in tag.attrs :
href = tag["href"]
if href.find(":") == -1 :
parts = href.split('#')
url = parts[0]
fragment = ""
if len(parts) > 1:
fragment = parts[1]
bookrelpath = os.path.join(currentdir, unquoteurl(url))
bookrelpath = os.path.normpath(bookrelpath)
bookrelpath = bookrelpath.replace(os.sep, "/")
if bookrelpath in updates:
attribute_value = updates[bookrelpath]
if fragment != "":
attribute_value = attribute_value + "#" + fragment
attribute_value = quoteurl(attribute_value)
tag["href"] = attribute_value
newdata = soup.decode(pretty_print=True, formatter='minimal')
return newdata
def anchorNCXUpdates(data, originating_filename, keylist, valuelist):
# rebuild serialized lookup dictionary
id_dict = {}
for i in range(0, len(keylist)):
id_dict[keylist[i]] = valuelist[i]
xmlbuilder = LXMLTreeBuilderForXML(parser=None,
empty_element_tags=ebook_xml_empty_tags)
soup = BeautifulSoup(data, features=None, builder=xmlbuilder)
original_filename_with_relative_path = TEXT_FOLDER_NAME + "/" + originating_filename
for tag in soup.find_all("content"):
if "src" in tag.attrs:
src = tag["src"]
if src.find(":") == -1:
parts = src.split('#')
if (parts is not None) and (len(parts) > 1) and (
parts[0] == original_filename_with_relative_path) and (
parts[1] != ""):
fragment_id = parts[1]
if fragment_id in id_dict:
attribute_value = TEXT_FOLDER_NAME + "/" + quoteurl(
id_dict[fragment_id]) + "#" + fragment_id
tag["src"] = attribute_value
newdata = soup.decodexml(indent_level=0,
formatter='minimal',
indent_chars=" ")
return newdata
def performNCXSourceUpdates(data, currentdir, keylist, valuelist):
# rebuild serialized lookup dictionary
updates = {}
for i in range(0, len(keylist)):
updates[keylist[i]] = valuelist[i]
xmlbuilder = LXMLTreeBuilderForXML(parser=None,
empty_element_tags=ebook_xml_empty_tags)
soup = BeautifulSoup(data, features=None, builder=xmlbuilder)
for tag in soup.find_all("content"):
if "src" in tag.attrs:
src = tag["src"]
if src.find(":") == -1:
parts = src.split('#')
url = parts[0]
fragment = ""
if len(parts) > 1:
fragment = parts[1]
bookrelpath = os.path.join(currentdir, unquoteurl(url))
bookrelpath = os.path.normpath(bookrelpath)
bookrelpath = bookrelpath.replace(os.sep, "/")
if bookrelpath in updates:
attribute_value = updates[bookrelpath]
if fragment != "":
attribute_value = attribute_value + "#" + fragment
attribute_value = quoteurl(attribute_value)
tag["src"] = attribute_value
newdata = soup.decodexml(indent_level=0,
formatter='minimal',
indent_chars=" ")
return newdata
def repairXML(data, self_closing_tags=ebook_xml_empty_tags, indent_chars=" "):
xmlbuilder = LXMLTreeBuilderForXML(parser=None,
empty_element_tags=self_closing_tags)
soup = BeautifulSoup(data, features=None, builder=xmlbuilder)
newdata = soup.decodexml(indent_level=0,
formatter='minimal',
indent_chars=indent_chars)
return newdata
def repairXML(data, self_closing_tags=ebook_xml_empty_tags):
xmlbuilder = LXMLTreeBuilderForXML(parser=None, empty_element_tags=self_closing_tags)
soup = BeautifulSoup(data, features=None, builder=xmlbuilder)
newdata = soup.decode(pretty_print=True, formatter='minimal')
return newdata