def setLandmarks(self, landmarks):
landmarks_xhtml = self.buildLandmarks(landmarks)
# replace the landmarks from the navsrc with a placeholer
navsrc = self.content
qp = QuickXHTMLParser()
qp.setContent(navsrc)
nav_type = None
res = []
skip_output = False
for txt, tp, tname, ttype, tattr in qp.parse_iter():
if txt is not None:
if not skip_output:
res.append(txt)
else:
if tname == "nav" and ttype == "begin":
nav_type = tattr.get("epub:type", None)
if nav_type is not None and nav_type == "landmarks":
res.append(SIGIL_REPLACE_LANDMARKS_HERE)
skip_output = True
continue
if tname == "nav" and ttype == "end" and nav_type == "landmarks":
nav_type = None
skip_output = False
continue
if not skip_output:
res.append(qp.tag_info_to_xml(tname, ttype, tattr))
navsrc = "".join(res)
m = re.search(NAV_LANDMARKS_PATTERN, navsrc)
if m is None:
return False
navsrc = navsrc[0:m.start()] + landmarks_xhtml + navsrc[m.end():]
self.content = navsrc
return True
def setTOC(self, toclist):
toc_xhtml = self.buildTOC(toclist)
# replace the TOC in the current navsrc with a placeholder
navsrc = self.content
qp = QuickXHTMLParser()
qp.setContent(navsrc)
nav_type = None
res = []
skip_output = False
for txt, tp, tname, ttype, tattr in qp.parse_iter():
if txt is not None:
if not skip_output:
res.append(txt)
else:
if tname == "nav" and ttype == "begin":
nav_type = tattr.get("epub:type", None)
if nav_type is not None and nav_type == "toc":
res.append(SIGIL_REPLACE_TOC_HERE)
skip_output = True
continue
if tname == "nav" and ttype == "end" and nav_type == "toc":
nav_type = None
skip_output = False
continue
if not skip_output:
res.append(qp.tag_info_to_xml(tname, ttype, tattr))
navsrc = "".join(res)
m = re.search(NAV_TOC_PATTERN, navsrc)
if m is None:
return False
navsrc = navsrc[0:m.start()] + toc_xhtml + navsrc[m.end():]
self.content = navsrc
return True
def setPageList(self, pagelist):
pagelist_xhtml = self.buildPageList(pagelist)
# replace the pagelist from the navsrc with a placeholer
navsrc = self.content
qp = QuickXHTMLParser()
qp.setContent(navsrc)
nav_type = None
res = []
skip_output = False
found_page_list = False
for txt, tp, tname, ttype, tattr in qp.parse_iter():
if txt is not None:
if not skip_output:
res.append(txt)
else:
if tname == "nav" and ttype == "begin":
nav_type = tattr.get("epub:type", None)
if nav_type is not None and nav_type == "page-list":
res.append(SIGIL_REPLACE_PAGELIST_HERE)
found_page_list = True
skip_output = True
continue
if tname == "nav" and ttype == "end" and nav_type == "page-list":
nav_type = None
skip_output = False
continue
if tname == "body" and ttype == "end":
if not found_page_list and len(pagelist) > 0:
padding = res[-1]
res.append(SIGIL_REPLACE_PAGELIST_HERE)
res.append(padding)
found_page_list = True
if not skip_output:
res.append(qp.tag_info_to_xml(tname, ttype, tattr))
navsrc = "".join(res)
m = re.search(NAV_PAGELIST_PATTERN, navsrc)
if m is None:
return False
navsrc = navsrc[0:m.start()] + pagelist_xhtml + navsrc[m.end():]
self.content = navsrc
return True
def getTOC(self):
# parse the nav to get the table of contents
navsrc = self.content
toclist = []
qp = QuickXHTMLParser()
qp.setContent(navsrc)
lvl = 0
po = 0
title = ""
nav_type = None
href = None
for txt, tp, tname, ttype, tattr in qp.parse_iter():
if txt is not None:
if ".a." in tp or tp.endswith(".a"):
title = title + txt
else:
title = ""
else:
if tname == "nav" and ttype == "begin":
nav_type = tattr.get("epub:type", None)
continue
if tname == "nav" and ttype == "end":
nav_type = None
continue
if nav_type is not None and nav_type == "toc":
if tname == "ol":
if ttype == "begin": lvl += 1
if ttype == "end": lvl -= 1
continue
if tname == "a" and ttype == "begin":
href = tattr.get("href", "")
# must leave all url hrefs in raw url encoded form
# if they can ever contain fragments
continue
if tname == "a" and ttype == "end":
po += 1
title = xmldecode(title)
toclist.append((po, lvl, href, title))
title = ""
href = None
continue
return toclist
def getLandmarks(self):
# parse the nav to get the landmarks
navsrc = self.content
landmarks = []
qp = QuickXHTMLParser()
qp.setContent(navsrc)
title = ""
nav_type = None
href = None
epubtype = None
for txt, tp, tname, ttype, tattr in qp.parse_iter():
if txt is not None:
if ".a." in tp or tp.endswith(".a"):
title = title + txt
else:
title = ""
else:
if tname == "nav" and ttype == "begin":
nav_type = tattr.get("epub:type", None)
continue
if tname == "nav" and ttype == "end":
nav_type = None
continue
if nav_type is not None and nav_type == "landmarks":
if tname == "a" and ttype == "begin":
href = tattr.get("href", "")
# must leave all hrefs in raw url encoded form
# if they can contain fragments
epubtype = tattr.get("epub:type", None)
continue
if tname == "a" and ttype == "end":
if epubtype is not None:
title = xmldecode(title)
landmarks.append((epubtype, href, title))
title = ""
epubtype = None
href = None
continue
return landmarks
def getPageList(self):
# parse the nav source to get the page-list
navsrc = self.content
pagelist = []
qp = QuickXHTMLParser()
qp.setContent(navsrc)
pgcnt = 0
nav_type = None
href = None
title = ""
for txt, tp, tname, ttype, tattr in qp.parse_iter():
if txt is not None:
if ".a." in tp or tp.endswith(".a"):
title = title + txt
else:
title = ""
else:
if tname == "nav" and ttype == "begin":
nav_type = tattr.get("epub:type", None)
continue
if tname == "nav" and ttype == "end":
nav_type = None
continue
if nav_type is not None and nav_type == "page-list":
if tname == "a" and ttype == "begin" and nav_type == "page-list":
href = tattr.get("href", "")
href = unquoteurl(href)
continue
if tname == "a" and ttype == "end":
pgcnt += 1
title = xmldecode(title)
pagelist.append((pgcnt, href, title))
title = ""
continue
return pagelist