def _parseData(self):
cnt = 0
for prefix, tname, tattr, tcontent in self._opf_tag_iter():
if self._debug:
print (" Parsing OPF: ", prefix, tname, tattr, tcontent)
# package
if tname == "package":
ver = tattr.pop("version", "2.0")
uid = tattr.pop("unique-identifier","bookid")
self.package = (ver, uid, tattr)
continue
# metadata
if tname == "metadata":
self.metadata_attr = tattr
continue
if tname in ["meta", "link"] or tname.startswith("dc:") and "metadata" in prefix:
self.metadata.append((tname, tattr, tcontent))
if tattr.get("name","") == "cover":
self.cover_id = tattr.get("content",None)
continue
# manifest
if tname == "item" and prefix.endswith("manifest"):
nid = "xid%03d" % cnt
cnt += 1
id = tattr.pop("id", nid)
href = tattr.pop("href",'')
mtype = tattr.pop("media-type",'')
if mtype == "text/html":
mtype = "application/xhtml+xml"
href = unquoteurl(href)
properties = tattr.pop("properties",None)
self.manifest_id_to_href[id] = href
self.manifest_id_to_mime[id] = mtype
self.href_to_manifest_id[href] = id
self.manifest_id_to_properties[id] = properties
continue
# spine
if tname == "spine":
if tattr is not None:
self.spine_ppd = tattr.get("page-progression-direction", None)
continue
if tname == "itemref" and prefix.endswith("spine"):
idref = tattr.pop("idref", "")
linear = tattr.pop("linear", None)
properties = tattr.pop("properties", None)
self.spine.append((idref, linear, properties))
continue
# guide
if tname == "reference" and prefix.endswith("guide"):
type = tattr.pop("type",'')
title = tattr.pop("title",'')
href = unquoteurl(tattr.pop("href",''))
self.guide.append((type, title, href))
continue
# bindings (stored but ignored for now)
if tname in ["mediaType", "mediatype"] and prefix.endswith("bindings"):
mtype = tattr.pop("media-type","")
handler = tattr.pop("handler","")
self.bindings.append((mtype, handler))
continue
def readotherfile(self, book_href):
id = unicode_str(book_href)
id = unquoteurl(id)
if id is None:
raise WrapperException('None is not a valid book href')
if id not in self.other and id in self.id_to_href:
raise WrapperException('Incorrect interface routine - use readfile')
# handle special case of trying to read the opf after it has been modified
if id == "OEBPS/content.opf":
if id in self.modified:
return self.build_opf()
filepath = self.book_href_to_filepath.get(id, None)
if filepath is None:
raise WrapperException('Book href does not exist')
basedir = self.ebook_root
if id in self.added or id in self.modified:
basedir = self.outdir
filepath = os.path.join(basedir, filepath)
if not unipath.exists(filepath):
raise WrapperException('File Does Not Exist')
basename = os.path.basename(filepath)
ext = os.path.splitext(basename)[1]
ext = ext.lower()
mime = ext_mime_map.get(ext,"")
data = b''
with open(filepath,'rb') as fp:
data = fp.read()
if mime in TEXT_MIMETYPES:
data = unicode_str(data)
return data
def getmime(self, href):
href = unicode_str(href)
href = unquoteurl(href)
filename = os.path.basename(href)
ext = os.path.splitext(filename)[1]
ext = ext.lower()
return ext_mime_map.get(ext, "")
def readotherfile(self, book_href):
id = unicode_str(book_href)
id = unquoteurl(id)
if id is None:
raise WrapperException('None is not a valid book href')
if id not in self.other and id in self.id_to_href:
raise WrapperException(
'Incorrect interface routine - use readfile')
# handle special case of trying to read the opf after it has been modified
if id == "OEBPS/content.opf":
if id in self.modified:
return self.build_opf()
filepath = self.book_href_to_filepath.get(id, None)
if filepath is None:
raise WrapperException('Book href does not exist')
basedir = self.ebook_root
if id in self.added or id in self.modified:
basedir = self.outdir
filepath = os.path.join(basedir, filepath)
if not unipath.exists(filepath):
raise WrapperException('File Does Not Exist')
basename = os.path.basename(filepath)
ext = os.path.splitext(basename)[1]
ext = ext.lower()
mime = ext_mime_map.get(ext, "")
data = b''
with open(filepath, 'rb') as fp:
data = fp.read()
if mime in TEXT_MIMETYPES:
data = unicode_str(data)
return data
def getmime(self, href):
href = unicode_str(href)
href = unquoteurl(href)
filename = os.path.basename(href)
ext = os.path.splitext(filename)[1]
ext = ext.lower()
return ext_mime_map.get(ext, "")
def deleteotherfile(self, book_href):
id = unicode_str(book_href)
id = unquoteurl(id)
if id is None:
raise WrapperException('None is not a valid book hrefbook href')
if id not in self.other and id in self.id_to_href:
raise WrapperException(
'Incorrect interface routine - use deletefile')
filepath = self.book_href_to_filepath.get(id, None)
if filepath is None:
raise WrapperException('Book href does not exist')
if id in PROTECTED_FILES:
raise WrapperException('attempt to delete protected file')
add_to_deleted = True
# if file was added or modified delete file from outdir
if id in self.added or id in self.modified:
filepath = os.path.join(self.outdir, filepath)
if unipath.exists(filepath) and unipath.isfile(filepath):
os.remove(filepath)
if id in self.added:
self.added.remove(id)
add_to_deleted = False
if id in self.other:
self.other.remove(id)
if id in self.modified:
del self.modified[id]
if add_to_deleted:
self.deleted.append(('other', id, book_href))
del self.book_href_to_filepath[id]
def deleteotherfile(self, book_href):
id = unicode_str(book_href)
id = unquoteurl(id)
if id is None:
raise WrapperException('None is not a valid book hrefbook href')
if id not in self.other and id in self.id_to_href:
raise WrapperException('Incorrect interface routine - use deletefile')
filepath = self.book_href_to_filepath.get(id, None)
if filepath is None:
raise WrapperException('Book href does not exist')
if id in PROTECTED_FILES:
raise WrapperException('attempt to delete protected file')
add_to_deleted = True
# if file was added or modified delete file from outdir
if id in self.added or id in self.modified:
filepath = os.path.join(self.outdir,filepath)
if unipath.exists(filepath) and unipath.isfile(filepath):
os.remove(filepath)
if id in self.added:
self.added.remove(id)
add_to_deleted = False
if id in self.other:
self.other.remove(id)
if id in self.modified:
del self.modified[id]
if add_to_deleted:
self.deleted.append(('other', id, book_href))
del self.book_href_to_filepath[id]
def _parseData(self):
for prefix, tname, tattr, tcontent in self._opf_tag_iter():
if self._debug:
print (" Parsing OPF: ", prefix, tname, tattr, tcontent)
# package
if tname == "package":
self.package_tag = [tname, tattr]
# metadata
if tname == "metadata":
self.metadata_tag = [tname, tattr]
if tname == "meta" or tname.startswith("dc:") and "metadata" in prefix:
self.metadata.append([tname, tattr, tcontent])
if tattr.get("name","") == "cover":
self.cover_id = tattr.get("content",None)
# manifest
if tname == "item" and prefix.endswith("manifest"):
id = tattr.pop("id",'')
href = tattr.pop("href",'')
mtype = tattr.pop("media-type",'')
if mtype == "text/html":
mtype = "application/xhtml+xml"
href = unquoteurl(href)
self.manifest_id_to_href[id] = href
self.manifest_id_to_mime[id] = mtype
self.href_to_manifest_id[href] = id
# spine
if tname == "spine":
if tattr is not None:
self.spine_ppd = tattr.get("page-progression-direction", None)
if tname == "itemref" and prefix.endswith("spine"):
idref = tattr.pop("idref", None)
linear = tattr.pop("linear", None)
self.spine.append((idref,linear))
# ver 3 allows page properites per page
# remove id since may be confusing
# if "id" in tattr:
# del tattr["id"]
# if "properties in tattr:
# self.spine_pageattributes[idref] = tattr
# guide
if tname == "reference" and prefix.endswith("guide"):
type = tattr.pop("type",'')
title = tattr.pop("title",'')
href = unquoteurl(tattr.pop("href",''))
self.guide.append((type, title, href))
def _parseData(self):
for prefix, tname, tattr, tcontent in self._opf_tag_iter():
if self._debug:
print(" Parsing OPF: ", prefix, tname, tattr, tcontent)
# package
if tname == "package":
self.package_tag = [tname, tattr]
# metadata
if tname == "metadata":
self.metadata_tag = [tname, tattr]
if tname == "meta" or tname.startswith(
"dc:") and "metadata" in prefix:
self.metadata.append([tname, tattr, tcontent])
if tattr.get("name", "") == "cover":
self.cover_id = tattr.get("content", None)
# manifest
if tname == "item" and prefix.endswith("manifest"):
id = tattr.pop("id", '')
href = tattr.pop("href", '')
mtype = tattr.pop("media-type", '')
href = unquoteurl(href)
self.manifest_id_to_href[id] = href
self.manifest_id_to_mime[id] = mtype
self.href_to_manifest_id[href] = id
# spine
if tname == "spine":
if tattr is not None:
self.spine_ppd = tattr.get("page-progession-direction",
None)
if tname == "itemref" and prefix.endswith("spine"):
idref = tattr.pop("idref", None)
linear = tattr.pop("linear", None)
self.spine.append((idref, linear))
# ver 3 allows page properites per page
# remove id since may be confusing
# if "id" in tattr:
# del tattr["id"]
# if "properties in tattr:
# self.spine_pageattributes[idref] = tattr
# guide
if tname == "reference" and prefix.endswith("guide"):
type = tattr.pop("type", '')
title = tattr.pop("title", '')
href = unquoteurl(tattr.pop("href", ''))
self.guide.append((type, title, href))
def setguide(self, new_guide):
guide = []
for (type, title, href) in new_guide:
type = unicode_str(type)
title = unicode_str(title)
href = unicode_str(href)
href = unquoteurl(href)
if type not in _guide_types:
type = "other." + type
if title is None:
title = 'title missing'
thref = href.split('#')[0]
if thref not in self.href_to_id:
raise WrapperException('guide href not in manifest')
guide.append((type, title, href))
self.guide = guide
self.modified['OEBPS/content.opf'] = 'file'
def setguide(self, new_guide):
guide = []
for (type, title, href) in new_guide:
type = unicode_str(type)
title = unicode_str(title)
href = unicode_str(href)
href = unquoteurl(href)
if type not in _guide_types:
type = "other." + type
if title is None:
title = 'title missing'
thref = href.split('#')[0]
if thref not in self.href_to_id:
raise WrapperException('guide href not in manifest')
guide.append((type, title, href))
self.guide = guide
self.modified['OEBPS/content.opf'] = 'file'
def writeotherfile(self, book_href, data):
id = unicode_str(book_href)
id = unquoteurl(id)
if id in self.id_to_href:
raise WrapperException('Incorrect interface routine - use writefile')
filepath = self.id_to_filepath.get(id, None)
if filepath is None:
raise WrapperException('book href does not exist')
if id in PROTECTED_FILES:
raise WrapperException('Attempt to modify protected file')
filepath = os.path.join(self.outdir, filepath)
base = os.path.dirname(filepath)
if not unipath.exists(base):
os.makedirs(base)
if isinstance(data, text_type):
data = utf8_str(data)
with open(filepath,'wb') as fp:
fp.write(data)
self.modified[id] = 'file'
def addotherfile(self, book_href, data):
id = unicode_str(book_href)
id = unquoteurl(id)
if id in self.other:
raise WrapperException('book href must be unquie')
desired_path = id.replace("/", os.sep)
filepath = os.path.join(self.outdir, desired_path)
if unipath.isfile(filepath):
raise WrapperException('desired path already exists')
base = os.path.dirname(filepath)
if not unipath.exists(base):
os.makedirs(pathof(base))
if isinstance(data, text_type):
data = utf8_str(data)
with open(pathof(filepath), 'wb') as fp:
fp.write(data)
self.other.append(id)
self.added.append(id)
self.id_to_filepath[id] = desired_path
def addotherfile(self, book_href, data) :
id = unicode_str(book_href)
id = unquoteurl(id)
if id in self.other:
raise WrapperException('book href must be unquie')
desired_path = id.replace("/",os.sep)
filepath = os.path.join(self.outdir,desired_path)
if unipath.isfile(filepath):
raise WrapperException('desired path already exists')
base = os.path.dirname(filepath)
if not unipath.exists(base):
os.makedirs(pathof(base))
if isinstance(data, text_type):
data = utf8_str(data)
with open(pathof(filepath),'wb')as fp:
fp.write(data)
self.other.append(id)
self.added.append(id)
self.id_to_filepath[id] = desired_path
def map_href_to_id(self, href, ow):
href = unicode_str(href)
href = unquoteurl(href)
return self.href_to_id.get(href, ow)
def map_href_to_id(self, href, ow):
href = unicode_str(href)
href = unquoteurl(href)
return self.href_to_id.get(href,ow)
def _parseData(self):
cnt = 0
for prefix, tname, tattr, tcontent in self._opf_tag_iter():
if self._debug:
print(" Parsing OPF: ", prefix, tname, tattr, tcontent)
# package
if tname == "package":
ver = tattr.pop("version", "2.0")
uid = tattr.pop("unique-identifier", "bookid")
self.package = (ver, uid, tattr)
continue
# metadata
if tname == "metadata":
self.metadata_attr = tattr
continue
if tname in ["meta", "link"
] or tname.startswith("dc:") and "metadata" in prefix:
self.metadata.append((tname, tattr, tcontent))
if tattr.get("name", "") == "cover":
self.cover_id = tattr.get("content", None)
continue
# manifest
if tname == "item" and prefix.endswith("manifest"):
nid = "xid%03d" % cnt
cnt += 1
id = tattr.pop("id", nid)
href = tattr.pop("href", '')
mtype = tattr.pop("media-type", '')
if mtype == "text/html":
mtype = "application/xhtml+xml"
href = unquoteurl(href)
properties = tattr.pop("properties", None)
self.manifest_id_to_href[id] = href
self.manifest_id_to_mime[id] = mtype
self.href_to_manifest_id[href] = id
self.manifest_id_to_properties[id] = properties
continue
# spine
if tname == "spine":
if tattr is not None:
self.spine_ppd = tattr.get("page-progression-direction",
None)
continue
if tname == "itemref" and prefix.endswith("spine"):
idref = tattr.pop("idref", "")
linear = tattr.pop("linear", None)
properties = tattr.pop("properties", None)
self.spine.append((idref, linear, properties))
continue
# guide
if tname == "reference" and prefix.endswith("guide"):
type = tattr.pop("type", '')
title = tattr.pop("title", '')
href = unquoteurl(tattr.pop("href", ''))
self.guide.append((type, title, href))
continue
# bindings (stored but ignored for now)
if tname in ["mediaTypes", "mediatypes"
] and prefix.endswith("bindings"):
mtype = tattr.pop("media-type", "")
handler = tattr.pop("handler", "")
self.bindings.append((mtype, handler))
continue