1
0
Fork 0
mat2/libmat2/epub.py

116 lines
4.4 KiB
Python
Raw Normal View History

2019-02-21 01:28:11 +01:00
import logging
import re
2019-02-27 23:04:38 +01:00
import uuid
import zipfile
2019-02-21 01:28:11 +01:00
import xml.etree.ElementTree as ET # type: ignore
2023-01-28 16:57:20 +01:00
from typing import Any, Dict
2019-02-21 01:28:11 +01:00
from . import archive, office
2023-01-28 16:57:20 +01:00
2019-04-27 13:05:36 +02:00
class EPUBParser(archive.ZipParser):
2019-02-21 01:28:11 +01:00
mimetypes = {'application/epub+zip', }
2019-02-27 23:04:38 +01:00
metadata_namespace = '{http://purl.org/dc/elements/1.1/}'
2019-02-21 01:28:11 +01:00
def __init__(self, filename):
super().__init__(filename)
self.files_to_keep = set(map(re.compile, { # type: ignore
'META-INF/container.xml',
'mimetype',
'OEBPS/content.opf',
2021-01-30 16:24:42 +01:00
'content.opf',
2021-02-07 17:17:16 +01:00
'hmh.opf',
'OPS/.+.xml'
2019-02-21 01:28:11 +01:00
}))
2021-02-07 17:17:16 +01:00
self.files_to_omit = set(map(re.compile, { # type: ignore
'iTunesMetadata.plist',
'META-INF/calibre_bookmarks.txt',
2021-03-07 16:59:18 +01:00
'OEBPS/package.opf',
2021-02-07 17:17:16 +01:00
}))
2019-02-27 23:04:38 +01:00
self.uniqid = uuid.uuid4()
2019-02-21 01:28:11 +01:00
def is_archive_valid(self):
super().is_archive_valid()
with zipfile.ZipFile(self.filename) as zin:
for item in self._get_all_members(zin):
member_name = self._get_member_name(item)
if member_name.endswith('META-INF/encryption.xml'):
raise ValueError('the file contains encrypted fonts')
2023-01-28 16:57:20 +01:00
def _specific_get_meta(self, full_path, file_path) -> Dict[str, Any]:
2021-02-07 17:17:16 +01:00
if not file_path.endswith('.opf'):
2019-02-21 01:28:11 +01:00
return {}
with open(full_path, encoding='utf-8') as f:
try:
results = re.findall(r"<((?:meta|dc|cp).+?)[^>]*>(.+)</\1>",
f.read(), re.I|re.M)
return {k:v for (k, v) in results}
except (TypeError, UnicodeDecodeError):
return {file_path: 'harmful content', }
2021-03-07 17:50:17 +01:00
def _specific_cleanup(self, full_path: str) -> bool:
2021-02-07 17:17:16 +01:00
if full_path.endswith('hmh.opf') or full_path.endswith('content.opf'):
2019-02-27 23:04:38 +01:00
return self.__handle_contentopf(full_path)
elif full_path.endswith('OEBPS/toc.ncx'):
return self.__handle_tocncx(full_path)
2021-02-07 17:17:16 +01:00
elif re.search('/OPS/[^/]+.xml$', full_path):
return self.__handle_ops_xml(full_path)
2019-02-27 23:04:38 +01:00
return True
2021-03-07 17:50:17 +01:00
def __handle_ops_xml(self, full_path: str) -> bool:
2021-02-07 17:17:16 +01:00
try:
tree, namespace = office._parse_xml(full_path)
except ET.ParseError: # pragma: nocover
logging.error("Unable to parse %s in %s.", full_path, self.filename)
return False
for item in tree.iterfind('.//', namespace): # pragma: nocover
if item.tag.strip().lower().endswith('head'):
item.clear()
break
tree.write(full_path, xml_declaration=True, encoding='utf-8',
short_empty_elements=False)
return True
2021-03-07 17:50:17 +01:00
def __handle_tocncx(self, full_path: str) -> bool:
2019-02-27 23:04:38 +01:00
try:
tree, namespace = office._parse_xml(full_path)
except ET.ParseError: # pragma: nocover
logging.error("Unable to parse %s in %s.", full_path, self.filename)
return False
for item in tree.iterfind('.//', namespace): # pragma: nocover
if item.tag.strip().lower().endswith('head'):
item.clear()
ET.SubElement(item, 'meta', attrib={'name': '', 'content': ''})
break
tree.write(full_path, xml_declaration=True, encoding='utf-8',
short_empty_elements=False)
return True
2019-02-21 01:28:11 +01:00
2021-03-07 17:50:17 +01:00
def __handle_contentopf(self, full_path: str) -> bool:
2019-02-21 01:28:11 +01:00
try:
tree, namespace = office._parse_xml(full_path)
except ET.ParseError:
logging.error("Unable to parse %s in %s.", full_path, self.filename)
return False
2019-02-27 23:04:38 +01:00
for item in tree.iterfind('.//', namespace): # pragma: nocover
2019-02-21 01:28:11 +01:00
if item.tag.strip().lower().endswith('metadata'):
2019-02-27 23:04:38 +01:00
item.clear()
# item with mandatory content
uniqid = ET.Element(self.metadata_namespace + 'identifier')
uniqid.text = str(self.uniqid)
uniqid.set('id', 'id')
item.append(uniqid)
# items without mandatory content
2021-11-21 11:02:22 +01:00
for name in ['language', 'title']:
2019-02-27 23:04:38 +01:00
uniqid = ET.Element(self.metadata_namespace + name)
item.append(uniqid)
2019-02-21 01:28:11 +01:00
break # there is only a single <metadata> block
2019-02-27 23:04:38 +01:00
tree.write(full_path, xml_declaration=True, encoding='utf-8')
2019-02-21 01:28:11 +01:00
return True