publite/backend
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Removed html escaping of book content

Browse Source
This commit is contained in:
Dmitriy Shishkov 2021-07-16 15:34:26 +05:00
parent d2adf23936
commit dcab64c78d
No known key found for this signature in database
GPG Key ID: 14358F96FCDD8060
2 changed files with 4 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
app/epub.py
View File

@ -108,7 +108,6 @@ async def epub_to_tokens(
def read_metadata(book: epub.EpubBook) -> dict[str, str]:
"""
Reads metadata from xml to dict
"""
@ -121,7 +120,6 @@ def read_metadata(book: epub.EpubBook) -> dict[str, str]:
def convert_list(titles_list: list[tuple[str, dict[str, str]]]) -> str:
"""
Joins titles list to one string
"""
@ -134,7 +132,6 @@ def convert_list(titles_list: list[tuple[str, dict[str, str]]]) -> str:
def set_cover(tokens: DocumentTokens) -> None:
"""
Converts cover file name to base64 image stored in `tokens`
"""
@ -145,7 +142,6 @@ def set_cover(tokens: DocumentTokens) -> None:
def epub_tokens2html(spine: list[tuple[str, str]], tokens: DocumentTokens) -> bytes:
"""
Joins chapters in `spice` to one html string
"""
@ -157,11 +153,10 @@ def epub_tokens2html(spine: list[tuple[str, str]], tokens: DocumentTokens) -> by
if file_path:
res += process_xhtml(file_path, tokens)
return html.escape(html.unescape(res))
return html.unescape(res)
def process_xhtml(path: str, tokens: DocumentTokens) -> bytes:
"""
Processes content of one xml body
"""
@ -179,7 +174,6 @@ def process_xhtml(path: str, tokens: DocumentTokens) -> bytes:
def process_content(node: etree.Element, path: str, tokens: DocumentTokens) -> None:
"""
Recursive function for xml element convertion to valid html
"""
@ -219,7 +213,6 @@ def process_content(node: etree.Element, path: str, tokens: DocumentTokens) -> N
def process_a_element(node: etree.Element, path: str):
r"""
Converts `filed` links to ids in \<a\> element
"""
@ -237,7 +230,6 @@ def process_a_element(node: etree.Element, path: str):
def process_media_element(node: etree.Element, path: str, tokens: DocumentTokens):
"""
Replaces file paths to base64 encoded media in `src` and `srcset` tags
"""
@ -256,7 +248,6 @@ def process_media_element(node: etree.Element, path: str, tokens: DocumentTokens
def rel_to_abs_path(parent: str, rel: str):
"""
Helper for relative path to media convertion to absolute
"""
@ -266,7 +257,6 @@ def rel_to_abs_path(parent: str, rel: str):
@cache
def path_to_name(path: str) -> str:
"""
Helper function for getting file name
"""
@ -275,7 +265,6 @@ def path_to_name(path: str) -> str:
def children_to_html(root: etree.Element) -> bytes:
"""
Converts all xml children of element to string and joins them
"""

13
app/fb2.py
View File

@ -32,7 +32,7 @@ async def fb22html(file: SpooledTemporaryFile) -> HTMLBook:
return {
**(tokens["metadata"]),
"content": html.escape(html.unescape(html_content.decode())),
"content": html.unescape(html_content.decode()),
}
except Exception as err:
@ -42,7 +42,6 @@ async def fb22html(file: SpooledTemporaryFile) -> HTMLBook:
def fb22tokens(file: SpooledTemporaryFile) -> DocumentTokens:
r"""
Parses fb2 file as xml document.
It puts book metadata, its content and media to `tokens` dictionary and returns it.
@ -78,7 +77,8 @@ def fb22tokens(file: SpooledTemporaryFile) -> DocumentTokens:
metadata = {}
metadata["title"] = book_info.find("./book-title", namespaces).text
metadata["author"] = get_author(book_info.find("./author", namespaces))
metadata["cover"] = get_cover(book_info.find("./coverpage", namespaces))
metadata["cover"] = get_cover(
book_info.find("./coverpage", namespaces))
if "cover" not in metadata.keys():
metadata.pop("cover")
@ -104,7 +104,6 @@ def fb22tokens(file: SpooledTemporaryFile) -> DocumentTokens:
def get_author(author: Element) -> str:
"""
Converts author xml structure to string
"""
@ -127,7 +126,6 @@ def get_author(author: Element) -> str:
def get_cover(coverpage: Optional[Element]) -> Optional[str]:
"""
Extracts cover image id if exists
"""
@ -148,7 +146,6 @@ def set_cover(tokens: DocumentTokens) -> None:
def fb2body2html(tokens: DocumentTokens) -> str:
"""
Convert fb2 xml to html, joins bodies into one string
"""
@ -163,7 +160,6 @@ def fb2body2html(tokens: DocumentTokens) -> str:
def process_section(body: Element, tokens: DocumentTokens) -> str:
"""
Processes individual sections, recursively goes throw sections tree
"""
@ -191,7 +187,6 @@ def process_section(body: Element, tokens: DocumentTokens) -> str:
def children_to_html(root: Element) -> str:
"""
Converts xml tag children to string
"""
@ -205,7 +200,6 @@ def children_to_html(root: Element) -> str:
def process_image(element: Element, tokens: DocumentTokens) -> None:
r"""
Converts fb2 \<image /\> to html \<img /\>. Replaces xlink:href with src="\<base64_image_data\>"
"""
@ -236,7 +230,6 @@ tag_with_class = {
def process_content(root: Element, tokens: DocumentTokens) -> None:
"""
Converts fb2 xml tag names to html equivalents and my own styled elements.
Resolves binary data dependencies