diff options
Diffstat (limited to 'libmat2/epub.py')
| -rw-r--r-- | libmat2/epub.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/libmat2/epub.py b/libmat2/epub.py index f43667e..83f5728 100644 --- a/libmat2/epub.py +++ b/libmat2/epub.py | |||
| @@ -2,6 +2,7 @@ import logging | |||
| 2 | import re | 2 | import re |
| 3 | import uuid | 3 | import uuid |
| 4 | import xml.etree.ElementTree as ET # type: ignore | 4 | import xml.etree.ElementTree as ET # type: ignore |
| 5 | from typing import Dict, Any | ||
| 5 | 6 | ||
| 6 | from . import archive, office | 7 | from . import archive, office |
| 7 | 8 | ||
| @@ -38,7 +39,7 @@ class EPUBParser(archive.ZipParser): | |||
| 38 | except (TypeError, UnicodeDecodeError): | 39 | except (TypeError, UnicodeDecodeError): |
| 39 | return {file_path: 'harmful content', } | 40 | return {file_path: 'harmful content', } |
| 40 | 41 | ||
| 41 | def _specific_cleanup(self, full_path: str): | 42 | def _specific_cleanup(self, full_path: str) -> bool: |
| 42 | if full_path.endswith('hmh.opf') or full_path.endswith('content.opf'): | 43 | if full_path.endswith('hmh.opf') or full_path.endswith('content.opf'): |
| 43 | return self.__handle_contentopf(full_path) | 44 | return self.__handle_contentopf(full_path) |
| 44 | elif full_path.endswith('OEBPS/toc.ncx'): | 45 | elif full_path.endswith('OEBPS/toc.ncx'): |
| @@ -47,7 +48,7 @@ class EPUBParser(archive.ZipParser): | |||
| 47 | return self.__handle_ops_xml(full_path) | 48 | return self.__handle_ops_xml(full_path) |
| 48 | return True | 49 | return True |
| 49 | 50 | ||
| 50 | def __handle_ops_xml(self, full_path: str): | 51 | def __handle_ops_xml(self, full_path: str) -> bool: |
| 51 | try: | 52 | try: |
| 52 | tree, namespace = office._parse_xml(full_path) | 53 | tree, namespace = office._parse_xml(full_path) |
| 53 | except ET.ParseError: # pragma: nocover | 54 | except ET.ParseError: # pragma: nocover |
| @@ -63,7 +64,7 @@ class EPUBParser(archive.ZipParser): | |||
| 63 | return True | 64 | return True |
| 64 | 65 | ||
| 65 | 66 | ||
| 66 | def __handle_tocncx(self, full_path: str): | 67 | def __handle_tocncx(self, full_path: str) -> bool: |
| 67 | try: | 68 | try: |
| 68 | tree, namespace = office._parse_xml(full_path) | 69 | tree, namespace = office._parse_xml(full_path) |
| 69 | except ET.ParseError: # pragma: nocover | 70 | except ET.ParseError: # pragma: nocover |
| @@ -79,7 +80,7 @@ class EPUBParser(archive.ZipParser): | |||
| 79 | short_empty_elements=False) | 80 | short_empty_elements=False) |
| 80 | return True | 81 | return True |
| 81 | 82 | ||
| 82 | def __handle_contentopf(self, full_path: str): | 83 | def __handle_contentopf(self, full_path: str) -> bool: |
| 83 | try: | 84 | try: |
| 84 | tree, namespace = office._parse_xml(full_path) | 85 | tree, namespace = office._parse_xml(full_path) |
| 85 | except ET.ParseError: | 86 | except ET.ParseError: |
