gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-04-02 02:13:38 +02:00
Code Issues Projects Releases Wiki Activity

Added first portion of logging adaptation.

Browse Source 
Things may be broken at this point - there are still several modules to
be adapted.
This commit is contained in:
gryf
2021-06-22 22:04:43 +02:00
parent 6f898ab23e
commit 546cc26652
36 changed files with 326 additions and 316 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
ebook_converter/ebooks/oeb/parse_utils.py
View File

@@ -65,7 +65,7 @@ def merge_multiple_html_heads_and_bodies(root, log=None):
body.append(x)
tuple(map(root.append, (head, body)))
if log is not None:
log.warn('Merging multiple <head> and <body> sections')
log.warning('Merging multiple <head> and <body> sections')
return root
@@ -122,7 +122,7 @@ def clean_word_doc(data, log):
for match in re.finditer(r'xmlns:(\S+?)=".*?microsoft.*?"', data):
prefixes.append(match.group(1))
if prefixes:
log.warn('Found microsoft markup, cleaning...')
log.warning('Found microsoft markup, cleaning...')
# Remove empty tags as they are not rendered by browsers
# but can become renderable HTML tags like <p/> if the
# document is parsed by an HTML parser
@@ -214,13 +214,13 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
data = etree.fromstring(data)
check_for_html5(pre, data)
except (HTML5Doc, etree.XMLSyntaxError):
log.debug('Parsing %s as HTML' % filename)
log.debug('Parsing %s as HTML', filename)
data = raw
try:
data = html5_parse(data)
except Exception:
log.exception(
'HTML 5 parsing failed, falling back to older parsers')
log.exception('HTML 5 parsing failed, falling back to older '
'parsers')
data = _html4_parse(data)
if has_html4_doctype or data.tag == 'HTML' or (len(data) and (data[-1].get('LANG') or data[-1].get('DIR'))):
@@ -239,7 +239,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
if barename(data.tag) != 'html':
if barename(data.tag) in non_html_file_tags:
raise NotHTML(data.tag)
log.warn('File %r does not appear to be (X)HTML'%filename)
log.warning('File %s does not appear to be (X)HTML', filename)
nroot = etree.fromstring('<html></html>')
has_body = False
for child in list(data):
@@ -248,7 +248,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
break
parent = nroot
if not has_body:
log.warn('File %r appears to be a HTML fragment'%filename)
log.warning('File %s appears to be a HTML fragment', filename)
nroot = etree.fromstring('<html><body/></html>')
parent = nroot[0]
for child in list(data.iter()):
@@ -260,7 +260,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
# Force into the XHTML namespace
if not namespace(data.tag):
log.warn('Forcing', filename, 'into XHTML namespace')
log.warning('Forcing %s into XHTML namespace', filename)
data.attrib['xmlns'] = const.XHTML_NS
data = etree.tostring(data, encoding='unicode')
@@ -272,10 +272,8 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
try:
data = etree.fromstring(data)
except etree.XMLSyntaxError:
log.warn('Stripping comments from %s'%
filename)
data = re.compile(r'<!--.*?-->', re.DOTALL).sub('',
data)
log.warning('Stripping comments from %s', filename)
data = re.compile(r'<!--.*?-->', re.DOTALL).sub('', data)
data = data.replace(
"<?xml version='1.0' encoding='utf-8'?><o:p></o:p>",
'')
@@ -283,7 +281,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
try:
data = etree.fromstring(data)
except etree.XMLSyntaxError:
log.warn('Stripping meta tags from %s'% filename)
log.warning('Stripping meta tags from %s', filename)
data = re.sub(r'<meta\s+[^>]+?>', '', data)
data = etree.fromstring(data)
elif namespace(data.tag) != const.XHTML_NS:
@@ -308,7 +306,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
head = xpath(data, '/h:html/h:head')
head = head[0] if head else None
if head is None:
log.warn('File %s missing <head/> element' % filename)
log.warning('File %s missing <head/> element', filename)
head = etree.Element(XHTML('head'))
data.insert(0, head)
title = etree.SubElement(head, XHTML('title'))
@@ -335,7 +333,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
body.getparent().remove(body)
data.append(body)
else:
log.warn('File %s missing <body/> element' % filename)
log.warning('File %s missing <body/> element', filename)
etree.SubElement(data, XHTML('body'))
# Remove microsoft office markup