def html_content_for(book, src_dir):
html_fpath = src_dir.joinpath(fname_for(book, "html"))
# is HTML file present?
if not html_fpath.exists():
logger.warn("Missing HTML content for #{} at {}".format(book.id, html_fpath))
return None, None
try:
return read_file(html_fpath)
except UnicodeDecodeError:
logger.error("Unable to read HTML content: {}".format(html_fpath))
raise
def html_content_for(book, static_folder, download_cache):
html_fpath = os.path.join(download_cache, fname_for(book, 'html'))
# is HTML file present?
if not path(html_fpath).exists():
logger.warn("Missing HTML content for #{} at {}"
.format(book.id, html_fpath))
return None, None
try:
return read_file(html_fpath)
except UnicodeDecodeError:
logger.error("Unable to read HTML content: {}".format(html_fpath))
raise
def html_content_for(book, static_folder, download_cache):
html_fpath = os.path.join(download_cache, fname_for(book, 'html'))
# is HTML file present?
if not path(html_fpath).exists():
logger.warn("Missing HTML content for #{} at {}"
.format(book.id, html_fpath))
return None, None
try:
return read_file(html_fpath)
except UnicodeDecodeError:
logger.error("Unable to read HTML content: {}".format(html_fpath))
raise
def handle_companion_file(fname,
dstfname=None,
book=None,
force=False,
as_ext=None):
ext = path(fname).ext if as_ext is None else as_ext
src = os.path.join(path(download_cache).abspath(), fname)
if dstfname is None:
dstfname = fname
dst = os.path.join(path(static_folder).abspath(), dstfname)
if path(dst).exists() and not force:
logger.debug("\t\tSkipping existing companion {}".format(dstfname))
return
# optimization based on mime/extension
if ext in (".png", ".jpg", ".jpeg", ".gif"):
logger.info(
"\t\tCopying and optimizing image companion {}".format(fname))
# copy_from_cache(src, dst)
optimize_image(src, dst)
elif ext == ".epub":
logger.info("\t\tCreating optimized EPUB file {}".format(fname))
tmp_epub = tempfile.NamedTemporaryFile(suffix=".epub",
dir=TMP_FOLDER)
tmp_epub.close()
try:
optimize_epub(src, tmp_epub.name)
except zipfile.BadZipFile:
logger.warn("\t\tBad zip file. "
"Copying as it might be working{}".format(fname))
handle_companion_file(fname,
dstfname,
book,
force,
as_ext="zip")
else:
path(tmp_epub.name).move(dst)
else:
# excludes files created by Windows Explorer
if src.endswith("_Thumbs.db"):
return
# copy otherwise (PDF mostly)
logger.debug("\t\tshitty ext: {}".format(dst))
logger.info("\t\tCopying companion file to {}".format(fname))
copy_from_cache(src, dst)
def handle_companion_file(fname, dstfname=None, book=None,
force=False, as_ext=None):
ext = path(fname).ext if as_ext is None else as_ext
src = os.path.join(path(download_cache).abspath(), fname)
if dstfname is None:
dstfname = fname
dst = os.path.join(path(static_folder).abspath(), dstfname)
if path(dst).exists() and not force:
logger.debug("\t\tSkipping existing companion {}".format(dstfname))
return
# optimization based on mime/extension
if ext in ('.png', '.jpg', '.jpeg', '.gif'):
logger.info("\t\tCopying and optimizing image companion {}"
.format(fname))
# copy_from_cache(src, dst)
optimize_image(src, dst)
elif ext == '.epub':
logger.info("\t\tCreating optimized EPUB file {}".format(fname))
tmp_epub = tempfile.NamedTemporaryFile(suffix='.epub',
dir=TMP_FOLDER)
tmp_epub.close()
try:
optimize_epub(src, tmp_epub.name)
except zipfile.BadZipFile:
logger.warn("\t\tBad zip file. "
"Copying as it might be working{}".format(fname))
handle_companion_file(fname, dstfname, book, force,
as_ext='zip')
else:
path(tmp_epub.name).move(dst)
else:
# excludes files created by Windows Explorer
if src.endswith('_Thumbs.db'):
return
# copy otherwise (PDF mostly)
logger.debug("\t\tshitty ext: {}".format(dst))
logger.info("\t\tCopying companion file to {}".format(fname))
copy_from_cache(src, dst)
def handle_companion_file(
fname,
dstfname=None,
book=None,
force=False,
as_ext=None,
html_file_list=None,
s3_storage=None,
):
ext = fname.suffix if as_ext is None else as_ext
src = fname
if dstfname is None:
dstfname = fname.name
dst = static_folder.joinpath(dstfname)
if dst.exists() and not force:
logger.debug("\t\tSkipping existing companion {}".format(dstfname))
return
# optimization based on mime/extension
if ext in (".png", ".jpg", ".jpeg", ".gif"):
logger.info("\t\tCopying and optimizing image companion {}".format(fname))
optimize_image(src, dst)
if dst.name == (f"{book.id}_cover_image.jpg") and s3_storage:
upload_to_cache(
asset=dst,
book_format="cover",
book_id=book.id,
etag=book.cover_etag,
s3_storage=s3_storage,
optimizer_version=optimizer_version,
)
update_download_cache(src, dst)
elif html_file_list:
html_file_list.append(dst)
update_download_cache(src, dst)
elif ext == ".epub":
logger.info("\t\tCreating optimized EPUB file {}".format(fname))
tmp_epub = tempfile.NamedTemporaryFile(suffix=".epub", dir=TMP_FOLDER)
tmp_epub.close()
try:
optimize_epub(src, tmp_epub.name)
except zipfile.BadZipFile:
logger.warn(
"\t\tBad zip file. "
"Copying as it might be working{}".format(fname)
)
handle_companion_file(fname, dstfname, book, force, as_ext=".zip")
else:
path(tmp_epub.name).move(dst)
if s3_storage:
upload_to_cache(
asset=dst,
book_format="epub",
book_id=book.id,
etag=book.epub_etag,
s3_storage=s3_storage,
optimizer_version=optimizer_version,
)
update_download_cache(src, dst)
else:
# excludes files created by Windows Explorer
if src.name.endswith("_Thumbs.db"):
return
# copy otherwise (PDF mostly)
logger.info("\t\tCopying companion file to {}".format(dst))
copy_file(src, dst)
if ext != ".pdf" and ext != ".zip" and html_file_list:
html_file_list.append(dst)
update_download_cache(src, dst)