github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Log warnings about files that would have been processed by disabled readers

Browse source
This commit is contained in:
boxydog 2024-06-17 08:11:21 -05:00
commit f19de98b9e
7 changed files with 119 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

39
pelican/readers.py
View file

@ -17,7 +17,7 @@ from pelican import rstdirectives # NOQA
from pelican.cache import FileStampDataCacher
from pelican.contents import Author, Category, Page, Tag
from pelican.plugins import signals
from pelican.utils import get_date, pelican_open, posixize_path
from pelican.utils import file_suffix, get_date, pelican_open, posixize_path
try:
from markdown import Markdown
@ -125,6 +125,10 @@ class BaseReader:
metadata = {}
return content, metadata
def disabled_message(self) -> str:
"""Message about why this plugin was disabled."""
return ""
class _FieldBodyTranslator(HTMLTranslator):
def __init__(self, document):
@ -347,6 +351,12 @@ class MarkdownReader(BaseReader):
metadata = {}
return content, metadata
def disabled_message(self) -> str:
return (
"Could not import markdown.Markdown. "
"Have you installed the markdown package?"
)
class HTMLReader(BaseReader):
"""Parses HTML files as input, looking for meta, title, and body tags"""
@ -508,17 +518,23 @@ class Readers(FileStampDataCacher):
def __init__(self, settings=None, cache_name=""):
self.settings = settings or {}
self.readers = {}
self.disabled_readers = {}
# extension => reader for readers that are enabled
self.reader_classes = {}
# extension => reader for readers that are not enabled
disabled_reader_classes = {}
for cls in [BaseReader] + BaseReader.__subclasses__():
if not cls.enabled:
logger.debug(
"Missing dependencies for %s", ", ".join(cls.file_extensions)
)
continue
for ext in cls.file_extensions:
self.reader_classes[ext] = cls
if cls.enabled:
self.reader_classes[ext] = cls
else:
disabled_reader_classes[ext] = cls
if self.settings["READERS"]:
self.reader_classes.update(self.settings["READERS"])
@ -531,6 +547,9 @@ class Readers(FileStampDataCacher):
self.readers[fmt] = reader_class(self.settings)
for fmt, reader_class in disabled_reader_classes.items():
self.disabled_readers[fmt] = reader_class(self.settings)
# set up caching
cache_this_level = (
cache_name != "" and self.settings["CONTENT_CACHING_LAYER"] == "reader"
@ -541,8 +560,13 @@ class Readers(FileStampDataCacher):
@property
def extensions(self):
"""File extensions that will be processed by a reader."""
return self.readers.keys()
@property
def disabled_extensions(self):
return self.disabled_readers.keys()
def read_file(
self,
base_path,
@ -562,8 +586,7 @@ class Readers(FileStampDataCacher):
logger.debug("Read file %s -> %s", source_path, content_class.__name__)
if not fmt:
_, ext = os.path.splitext(os.path.basename(path))
fmt = ext[1:]
fmt = file_suffix(path)
if fmt not in self.readers:
raise TypeError("Pelican does not know how to parse %s", path)
@ -654,6 +677,12 @@ class Readers(FileStampDataCacher):
context=context,
)
def check_file(self, source_path: str) -> None:
"""Log a warning if a file is processed by a disabled reader."""
reader = self.disabled_readers.get(file_suffix(source_path), None)
if reader:
logger.warning(f"{source_path}: {reader.disabled_message()}")
def find_empty_alt(content, path):
"""Find images with empty alt