def _get_document_parts_for_ref(self, module_name, ref, do_current_ref=True):
t = default_timer()
stylesheets = list(self.bible_stylesheets)
scripts = self.standard_scripts + self.bible_scripts + ["highlight.js", "bpbible_html.js", "contrib/hyphenate.js", "columns.js"]
book = biblemgr.get_module_book_wrapper(module_name)
assert book, "Module wrapper not found for book " + module_name
module = book.mod
if book.chapter_view:
scripts.append("bpbible_html_chapter_view.js")
#stylesheets.append("bpbible_chapter_view.css")
#stylesheets.append("bpbible://content/quotes_skin/")
else:
scripts.append("bpbible_html_page_view.js")
stylesheets.append("bpbible_page_view.css")
if is_debugging():
stylesheets.append("bpbible_html_debug.css")
if book.is_verse_keyed:
if book.chapter_view:
if do_current_ref:
c = book.GetChapter(ref, ref, config.current_verse_template)
else:
c = book.GetChapter(ref)
ref_id = VK(ref).get_chapter_osis_ref()
else:
c = book.GetReference(ref, headings=True)
ref_id = VK(ref).getOSISRef()
elif book.is_dictionary:
c = book.GetReference(ref)
ref_id = ref
elif book.is_genbook:
c = book.GetReference(ref)
ref_id = ref
else:
dprint(ERROR, "Book `%s' not found." % module_name)
c = ''
c = c.replace("<!P>", "</p><p>")
clas = ""
if not c:
clas = " nocontent"
lang = module.Lang() if module else "en",
c = convert_language(c, lang)
c = '<div class="segment%s" ref_id="%s">%s</div>' % (clas, urllib.quote(ref_id.encode("utf8")), c)
return dict(
module=module, content=c,
bodyattrs=self._get_body_attrs(module),
stylesheets=stylesheets,
scripts=scripts,
timer="<div class='timer'>Time taken: %.3f (ref_id %s)</div>" % (default_timer() - t, ref_id))
def _get_html(self,
module,
content,
bodyattrs="",
timer="",
stylesheets=[],
scripts=[],
javascript_block="",
styles="",
contentclass="",
include_wrapper_divs=True):
resources = []
### Should we keep using the file:/// protocol?
### For the XUL port we intended to switch to using the chrome:/// protocol.
prefix = "file:///" + os.getcwd() + "/"
css_dir = "css"
script_dir = "js"
for item in stylesheets:
if "://" in item:
resources.append(
'<link rel="stylesheet" type="text/css" href="%s"/ >' %
(item))
else:
resources.append(
'<link rel="stylesheet" type="text/css" href="%s/%s/%s"/ >'
% (prefix, css_dir, item))
for item in scripts:
resources.append(
'<script type="text/javascript" src="%s/%s/%s"></script>' %
(prefix, script_dir, item))
if styles:
resources.append('<style type="text/css">%s</style>' % styles)
if javascript_block:
resources.append('<script type="text/javascript">%s</script>' %
javascript_block)
if include_wrapper_divs:
content = '<div id="content" class="%(contentclass)s">\n%(content)s\n</div>' % locals(
)
text = BASE_HTML % dict(lang=module.Lang() if module else "en",
head='\n'.join(resources),
bodyattrs=bodyattrs,
content=content,
timer=timer)
if is_debugging():
self.log_generated_html(text)
return text
def _get_html(self, module, content, bodyattrs="", timer="",
stylesheets=[], scripts=[], javascript_block="", styles="", contentclass="",
include_wrapper_divs=True):
resources = []
### Should we keep using the file:/// protocol?
### For the XUL port we intended to switch to using the chrome:/// protocol.
prefix = "file:///" + os.getcwd() + "/"
css_dir = "css"
script_dir = "js"
for item in stylesheets:
if "://" in item:
resources.append('<link rel="stylesheet" type="text/css" href="%s"/ >' % (item))
else:
resources.append('<link rel="stylesheet" type="text/css" href="%s/%s/%s"/ >' % (prefix, css_dir, item))
for item in scripts:
resources.append('<script type="text/javascript" src="%s/%s/%s"></script>' % (prefix, script_dir, item))
if styles:
resources.append('<style type="text/css">%s</style>' % styles)
if javascript_block:
resources.append('<script type="text/javascript">%s</script>' % javascript_block)
if include_wrapper_divs:
content = '<div id="content" class="%(contentclass)s">\n%(content)s\n</div>' % locals()
text = BASE_HTML % dict(
lang=module.Lang() if module else "en",
head='\n'.join(resources),
bodyattrs=bodyattrs,
content=content,
timer=timer)
if is_debugging():
self.log_generated_html(text)
return text
class IndexedText(object):
"""A bit of text, one reference per line, with an index built against it"""
gatherstatistics = True
def __init__(self, version, bookname=None, create_index=True):
self.index = [] # ref, start, length
self.text = ""
self.field_data = {}
self.bookname = bookname or version
self.version = version
module = self.load_module(version)
self.errors_on_collection = []
self._has_xml_errors = False
if create_index:
self.collect_text(module)
def collect_text(self, module):
"""Collect the text for a given module, into a reference per line
format, then build an index against it"""
# this is a guaranteed non-character...
# so it shouldn't be used in text
# http://en.wikibooks.org/wiki/Unicode/Character_reference/F000-FFFF
MAGIC_TOKEN = u"\uFDD0"
xml_token = "&#%d;" % ord(MAGIC_TOKEN)
items = []
old_key = module.getKey()
if not ord(old_key.Persist()):
# if it wasn't a persistent key, the module owns it
# so take a copy of it, and say we own it
old_key = old_key.clone()
old_key.thisown = True
entries = self.get_entries()
key = self.get_key(module)
key.Persist(1)
module.setKey(key)
if not entries:
module.setPosition(TOP)
key_entry = self.get_key_entry(key)
# clear the error
module.Error()
i = 0
if not entries:
entries = sys.maxint
# gather the text
while not ord(module.Error()) and i < entries:
items.append((key_entry(), module.getRawEntry()))
module.increment(1)
i += 1
# the key's headings attribute gets set to 1 at the end of the
# previous loop...
if isinstance(key, VK): key.Headings(0)
# try and do smart parsing
content = None
processor = {
SW.FMT_OSIS: process_text.ParseOSIS,
SW.FMT_THML: process_text.ParseThML,
}.get(ord(module.Markup()), None)
if processor:
xml_items = [
"<KeyedEntry key='%s'>%s</KeyedEntry>" % i for i in items
]
# fix its encoding if necessary
if ord(module.Encoding()) == SW.ENC_LATIN1:
xml_items = [
# ignore any errors
item.decode("cp1252", "ignore").encode("utf8", "ignore")
for item in xml_items
]
try:
content = processor().parse(xml_token.join(xml_items))
except Exception, e:
self._has_xml_errors = True
import traceback
traceback.print_exc(file=sys.stdout)
print self.get_key(module).getText()
if content is None:
# fallback, don't want to have to do this...
# encode the token as utf-8 so that we end up with a string from
# here
content = MAGIC_TOKEN.encode("utf8").join(
module.StripText(item) for key, item in items)
content = content.decode("utf-8", "ignore")
content = removeformatting(content)
self.text = re.sub("\s*%s\s*" % MAGIC_TOKEN, "\n", content)
self.text, self.field_data = self.extract_strongs(self.text)
if self.text.count('\n') + 1 != len(items):
# it is possible that decoding the utf8 of the book above
# may lead to problems which will gobble up our magic token
# so we check that we have the expected number here. If we don't,
# scream, as it may lead to incorrect results
self.errors_on_collection.append(
_("Invalid encoding: Searching may not work or may "
"display the wrong results"))
if is_debugging():
for k, item in items:
try:
# TODO: sword ThMLPlain filter outputs &...; as
# latin1, not utf-8. This makes big problems...
module.StripText(item).decode("utf-8")
except UnicodeDecodeError:
self.errors_on_collection.append(k)
self.create_index_against_text(module, key)
module.setKey(old_key)
# IMPORTANT: clear the error indicator
# otherwise the highlighted search frame may end up blank the first
# time the user uses it!
module.Error()
def SetWebPreferences(self):
prefs = wx.wc.WebControl.preferences
prefs['browser.dom.window.dump.enabled'] = is_debugging()
if sys.argv[1].endswith(".py"):
f = sys.argv.pop(1)
return execfile(f, globals(), globals())
inspection_imported = False
try:
from wx.lib.mixins.inspect import InspectionMixin
inspection_imported = True
except ImportError, e:
try:
from wx.lib.mixins.inspection import InspectionMixin
inspection_imported = True
except ImportError, e:
pass
if inspection_imported and is_debugging():
class InspectableApp(MyApp, InspectionMixin):
def OnInit(self):
return_value = super(InspectableApp, self).OnInit()
if not return_value:
return False
self.Init()
return True
app = InspectableApp(0)
else:
if is_debugging():
dprint(WARNING, "Could not load inspection")
app = MyApp(0)
def _get_document_parts_for_ref(self,
module_name,
ref,
do_current_ref=True):
t = default_timer()
stylesheets = list(self.bible_stylesheets)
scripts = self.standard_scripts + self.bible_scripts + [
"highlight.js", "bpbible_html.js", "contrib/hyphenate.js",
"columns.js"
]
book = biblemgr.get_module_book_wrapper(module_name)
assert book, "Module wrapper not found for book " + module_name
module = book.mod
if book.chapter_view:
scripts.append("bpbible_html_chapter_view.js")
#stylesheets.append("bpbible_chapter_view.css")
#stylesheets.append("bpbible://content/quotes_skin/")
else:
scripts.append("bpbible_html_page_view.js")
stylesheets.append("bpbible_page_view.css")
if is_debugging():
stylesheets.append("bpbible_html_debug.css")
if book.is_verse_keyed:
if book.chapter_view:
if do_current_ref:
c = book.GetChapter(ref, ref,
config.current_verse_template)
else:
c = book.GetChapter(ref)
ref_id = VK(ref).get_chapter_osis_ref()
else:
c = book.GetReference(ref, headings=True)
ref_id = VK(ref).getOSISRef()
elif book.is_dictionary:
c = book.GetReference(ref)
ref_id = ref
elif book.is_genbook:
c = book.GetReference(ref)
ref_id = ref
else:
dprint(ERROR, "Book `%s' not found." % module_name)
c = ''
c = c.replace("<!P>", "</p><p>")
clas = ""
if not c:
clas = " nocontent"
lang = module.Lang() if module else "en",
c = convert_language(c, lang)
c = '<div class="segment%s" ref_id="%s">%s</div>' % (
clas, urllib.quote(ref_id.encode("utf8")), c)
return dict(
module=module,
content=c,
bodyattrs=self._get_body_attrs(module),
stylesheets=stylesheets,
scripts=scripts,
timer="<div class='timer'>Time taken: %.3f (ref_id %s)</div>" %
(default_timer() - t, ref_id))
if sys.argv[1].endswith(".py"):
f = sys.argv.pop(1)
return execfile(f, globals(), globals())
inspection_imported = False
try:
from wx.lib.mixins.inspect import InspectionMixin
inspection_imported = True
except ImportError, e:
try:
from wx.lib.mixins.inspection import InspectionMixin
inspection_imported = True
except ImportError, e:
pass
if inspection_imported and is_debugging():
class InspectableApp(MyApp, InspectionMixin):
def OnInit(self):
return_value = super(InspectableApp, self).OnInit()
if not return_value:
return False
self.Init()
return True
app = InspectableApp(0)
else:
if is_debugging():
dprint(WARNING, "Could not load inspection")
app = MyApp(0)