def html_tick(fname):
global conf, mw
conf.recurse = False
try:
fh = open(fname)
ht = pubhtml.HTML_Parser(conf)
ht.mw = mw
ht.fh = fh
ht.getimagecb = getimagecb
ln = 0
mw.waitcursor(True)
while 1:
if conf.recurse:
break
sss = fh.readline()
if ln % 10 == 0:
mw.prog.set_text("Reading line: %d" % ln)
usleep(1)
ln += 1
if sss == "": break
if conf.recurse:
break
if ht.feed(sss):
break
mw.add_text(sss, True)
mw.fname = fname
mw.waitcursor(False)
except:
print_exception("Opening HTML")
mw.prog.set_text("Done Loading.")
mw.hpaned.set_position(0)
mw.gohome()
def read_tts(self, butt):
self.view.grab_focus()
# Running?
self.stopspeak = True
if self.speech_pid:
self.stop_tts()
return
self.prog.set_text("Started Reading")
cstr = ""
iters = self.buffer_1.get_selection_bounds()
if iters:
cstr = self.buffer_1.get_text(iters[0], iters[1])
if cstr:
self.butt4.set_label("S_top")
gobject.timeout_add(100, self.speak, cstr)
else:
self.stopspeak = False
# Speak from current location, para by para
iter = self.buffer_1.get_iter_at_mark(self.buffer_1.get_insert())
if not iter:
iter = self.buffer_1.get_start_iter()
iterx = iter.copy()
while True:
# Adapt new position if changed
iter3 = self.buffer_1.get_iter_at_mark(
self.buffer_1.get_insert())
#if iterx.get_offset() != iter3.get_offset():
# iterx = iter3.copy
# iter = iter3.copy()
iter2 = iter.copy
eiter = iter.forward_search("\n", 0)
if eiter:
iter2 = eiter[1]
else:
iter2 = iter.copy()
iter2.forward_sentence_end()
self.view.scroll_to_iter(iter, 0.2) #, True, 0, 0)
self.view.place_cursor_onscreen()
self.buffer_1.select_range(iter, iter2)
cstr = self.buffer_1.get_text(iter, iter2)
if self.stopspeak:
break
if cstr != "\n":
self.butt4.set_label("S_top")
# Speak and wait for it to finish
self.speak(cstr)
while True:
if not self.speech_pid:
break
pubutil.usleep(100)
iter = iter2
# End of buffer?
if iter2.get_offset() >= \
self.buffer_1.get_end_iter().get_offset():
self.gohome()
break
if self.stopspeak:
break
def readepub(zf):
global mw, basefile, ht, conf
names = []; allnames = []
mw.waitcursor(True)
for aa in zf.infolist():
#print aa.filename, aa.file_size,
# Extract
if conf.extract:
try:
dd = conf.data_dir + "/" + basefile + "/" + os.path.split(aa.filename)[0]
if not os.path.isdir(dd):
os.makedirs(dd)
fh = zf.open(aa.filename)
fff = dd + "/" + os.path.basename(aa.filename)
# Only extract once:
if not os.path.isfile(fff):
mw.prog.set_text("Extracting '" + aa.filename + "'")
usleep(1)
fh2 = open(fff, "w+")
while 1:
sss = fh.readline()
if sss == "": break
fh2.write(sss)
fh2.close()
except:
print_exception("Cannot extract file")
if os.path.splitext(aa.filename)[1].find("htm") >= 0:
names.append(aa.filename)
allnames.append(aa.filename)
#print
#names.sort(cmp)
#print names
found = False
for aa in allnames:
if "toc.ncx" in aa:
#print "Found toc", aa
found = True
fh = zf.open(aa)
ht = TocHTMLParser(mw)
while 1:
sss = fh.readline()
if sss == "": break
ht.feed(sss)
mw.add_text(sss, True)
break
# No TOC Open and parse all the [x]htm[l] files
if not found:
nnn = "000"; mw.update_tree("Start", nnn); mw.add_text_mark(nnn)
for bbb in names:
openHTML(zf, bbb)
nnn = "999"; mw.update_tree("End", nnn); mw.add_text_mark(nnn)
mw.waitcursor(False)
def reader_tick():
global mw
fh = open(args[0])
while 1:
sss = fh.readline()
if sss == "":
break
#print "got", sss
mw.add_text(sss, True)
mw.prog.set_text("Reading %d" % fh.tell())
usleep(1)
mw.par.feed(sss)
fh.close()
def openHTMLcb(fname, addback=True):
global conf, gzf, backlist
ret = False
#print "openHTMLcb", fname
conf.recurse = True
usleep(10)
try:
if addback:
backlist.append(fname)
ret = openHTML(gzf, fname, False)
gobject.timeout_add(100, size_tick)
except:
print_exception("Cannot load HTML")
conf.recurse = False
return ret
def openHTML(zf, fname, mark=True):
global conf
found = False
fh = None
spl = []
ht = None
conf.recurse = False
# Is it a link with a tag?
spl = fname.split("#")
# Not loaded, load
if mw.fname != spl[0]:
mw.clearall()
found = False
fh = None
usleep(1)
try:
fh = zf.open(spl[0])
found = True
except:
for aa in zf.infolist():
if os.path.basename(aa.filename) == os.path.basename(spl[0]):
#print "found", aa.filename
try:
fh = zf.open(aa.filename)
except:
print_exception("No Zip File")
return
found = True
break
if not found: return False
try:
ht = pubhtml.HTML_Parser(conf)
ht.mw = mw
ht.mark = mark
ht.fh = fh
ht.getimagecb = getimagecb
ln = 0
mw.waitcursor(True)
while 1:
if conf.recurse:
break
if mw.stopload:
break
sss = fh.readline()
if mw.stopload:
break
if ln % 10 == 0:
mw.prog.set_text("Reading line: %d" % ln)
usleep(1)
ln += 1
if sss == "": break
if conf.recurse:
break
if ht.feed(sss):
break
mw.add_text(sss, True)
mw.fname = spl[0]
mw.waitcursor(False)
except:
print_exception("Parsing HTML")
#if mw.stopload:
# return
mw.prog.set_text("Done Loading.")
usleep(10)
if mw.stopload:
return
# Jump to tag, if any
if len(spl) > 1:
#print "Jumping to", "'" + spl[1] + "'"
mm = mw.buffer_1.get_mark(spl[1])
if mm:
ii = mw.buffer_1.get_iter_at_mark(mm)
mw.buffer_1.place_cursor(ii)
mw.view.scroll_to_mark(mm, 0.0, True, 0, 0)
else:
mw.gohome()
return True
def readepub(zf):
global mw, conf
names = []
allnames = []
if not conf.nogui:
mw.waitcursor(True)
if conf.extract:
print "Extracting epub to:", conf.data_dir + "/" + conf.basefile + "/"
for aa in zf.infolist():
if conf.list:
print aa.filename, aa.file_size
# Extract
if conf.extract:
try:
dd = conf.data_dir + "/" + conf.basefile + "/" + os.path.split(
aa.filename)[0]
if not os.path.isdir(dd):
os.makedirs(dd)
fh = zf.open(aa.filename)
fff = dd + "/" + os.path.basename(aa.filename)
# Only extract once:
if not os.path.isfile(fff):
if not conf.nogui:
tt = "Extracting '" + aa.filename + "'"
mw.prog.set_text(tt[-18])
usleep(1)
fh2 = open(fff, "w+")
while 1:
sss = fh.readline()
if sss == "": break
fh2.write(sss)
fh2.close()
except:
print_exception("Cannot extract file")
if os.path.splitext(aa.filename)[1].find("htm") >= 0:
names.append(aa.filename)
allnames.append(aa.filename)
found = False
ret1 = None
ret2 = None
'''rootfile = locateroot()
print "rootfile:", rootfile
if rootfile != "":
found = True
if ".ncx" in rootfile:
ret1 = parse_ncs(rootfile)
if ".opf" in rootfile:
ret2 = parse_opf(rootfile)'''
# Hack: to simplify parsing we search for an .ncx and .opf file
if not found:
for aa in allnames:
if ".ncx" in aa:
#print "Found toc", aa
#found = True
ret1 = parse_ncx(aa)
break
if not conf.nogui:
mw.update_tree(" --------- ", "")
# Fallback
if not found:
for aa in allnames:
if ".opf" in aa:
#print "Found opf", aa
found = True
ret2 = parse_opf(aa)
break
# Pick from the two optional places
auth = ret1[0]
try:
if auth == "": auth = ret2[0]
except:
pass
title = ret1[1]
try:
if title == "": title = ret2[1]
except:
pass
if conf.title:
print "'" + auth + "' '" + title + "'"
if not conf.nogui:
old = mw.get_title()
mw.set_title(old + " '" + auth + "' '" + title + "'")
if conf.nogui:
return
# No TOC Open and parse all the [x]htm[l] files
if not found:
nnn = "000"
mw.update_tree("Start of Book", nnn)
mw.add_text_mark(nnn)
for bbb in names:
openHTML(zf, bbb)
nnn = "999"
mw.update_tree("End", nnn)
mw.add_text_mark(nnn)
mw.waitcursor(False)
def readepub(zf):
global mw, conf
names = []
allnames = []
if not conf.nogui:
mw.waitcursor(True)
if conf.extract:
print "Extracting epub to:", conf.data_dir + "/" + conf.basefile + "/"
# Locate root meta data
try:
md = zf.open("META-INF/container.xml")
if conf.rootf:
print md.read()
except:
print "No meta data, guessing"
for aa in zf.infolist():
if conf.list:
print aa.filename, aa.file_size
# Extract
if conf.extract:
try:
dd = conf.data_dir + "/" + conf.basefile + "/" + os.path.split(
aa.filename)[0]
if not os.path.isdir(dd):
os.makedirs(dd)
fh = zf.open(aa.filename)
fff = dd + "/" + os.path.basename(aa.filename)
# Only extract once:
if not os.path.isfile(fff):
if not conf.nogui:
tt = "Extracting '" + aa.filename + "'"
mw.prog.set_text(tt[-18])
usleep(1)
fh2 = open(fff, "w+")
while 1:
sss = fh.readline()
if sss == "": break
fh2.write(sss)
fh2.close()
except:
print_exception("Cannot extract file")
if os.path.splitext(aa.filename)[1].find("htm") >= 0:
names.append(aa.filename)
allnames.append(aa.filename)
found = False
ht = None
ht2 = None
for aa in allnames:
if "toc.ncx" in aa:
#print "Found toc", aa
found = True
fh = zf.open(aa)
ht = TocHTMLParser(contentcb)
conf.ht = ht
while 1:
sss = fh.readline()
if sss == "": break
ht.feed(sss)
if conf.header:
print sss,
if not conf.nogui:
mw.add_text(sss, True)
break
if 1:
for aa in allnames:
if "content.opf" in aa:
if not conf.nogui:
mw.update_tree("Legacy Entries:", [])
#print "Found content", aa
found = True
fh = zf.open(aa)
ht2 = ConHTMLParser(content2cb)
while 1:
sss = fh.readline()
if sss == "": break
if conf.header:
print sss,
ht2.feed(sss)
if conf.header:
print sss,
if not conf.nogui:
mw.add_text(sss, True)
break
auth = ""
title = ""
try:
auth = ht.auth
except:
pass
try:
if auth == "": auth = ht2.auth
except:
pass
try:
title = ht.title
except:
pass
try:
if title == "": title = ht2.title
except:
pass
if conf.title:
print "'" + auth + "' '" + title + "'"
if not conf.nogui:
old = mw.get_title()
mw.set_title(old + " '" + auth + "' '" + title + "'")
if conf.nogui:
return
# No TOC Open and parse all the [x]htm[l] files
if not found:
nnn = "000"
mw.update_tree("Start of Book", nnn)
mw.add_text_mark(nnn)
for bbb in names:
openHTML(zf, bbb)
nnn = "999"
mw.update_tree("End", nnn)
mw.add_text_mark(nnn)
mw.waitcursor(False)
return ht
def openHTML(zf, fname, mark=True):
global conf
# Is it a tagged link?
ppp = fname.find("#")
spl = []
if spl >= 0:
spl = fname.split("#")
fname = spl[0]
# Not loaded, load
if mw.fname != fname:
#print "loading", fname
mw.clear()
mw.clear(True)
found = False
fh = None
try:
fh = zf.open(fname)
found = True
except:
#print "searching for", fname, sys.exc_info()
# Search for it ...
for aa in zf.infolist():
#print aa.filename, fname
if os.path.basename(aa.filename) == fname:
try:
fh = zf.open(aa.filename)
except:
print_exception("No Zip File")
return
found = True
break
if not found: return False
try:
ht = pubhtml.HTML_Parser(conf)
ht.mw = mw
ht.mark = mark
ht.fh = fh
ht.getimagecb = getimagecb
ln = 0
mw.waitcursor(True)
while 1:
sss = fh.readline()
if ln % 10 == 0:
mw.prog.set_text("Reading line: %d" % ln)
usleep(1)
ln += 1
if sss == "": break
if ht.feed(sss):
break
mw.add_text(sss, True)
mw.fname = fname
mw.waitcursor(False)
except:
print_exception("Parsing HTML")
mw.prog.set_text("Done Reading.")
usleep(10)
# Jump to tag, if any
if len(spl) > 1:
#print "Jumping to", "'" + spl[1] + "'"
mm = mw.buffer_1.get_mark(spl[1])
ii = mw.buffer_1.get_iter_at_mark(mm)
if mm:
mw.view.scroll_to_mark(mm, 0.0, True, 0, 0)
else:
mw.gohome()
return True
