def handleText(self, text, format=None, stx_level=None):
""" Handles the raw text, returning headers, body, format """
headers = {}
if not format:
format = self.guessFormat(text)
if format == 'html':
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title:
headers['Title'] = parser.title
body = bodyfinder(text)
else:
headers, body = parseHeadersBody(text, headers)
if stx_level:
self._stx_level = stx_level
return headers, body, format
def handleText(self, text, format=None, stx_level=None):
""" Handles the raw text, returning headers, body, format """
headers = {}
if not format:
format = self.guessFormat(text)
if format == 'html':
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title:
headers['Title'] = parser.title
body = bodyfinder(text)
else:
headers, body = parseHeadersBody(text, headers)
if stx_level:
self._stx_level = stx_level
return headers, body, format
def edit(self, text_format, text, file=''):
"""
Edit the Document
"""
self.text = text
headers = {}
if file and (type(file) is not type('')):
contents = file.read()
if contents:
text = self.text = contents
# Now parse out HTML if its applicable, or the plain text,
# getting any headers passed along in the document
bodyfound = bodyfinder.search(text)
ishtml = (text_format == 'html') or (bodyfound is not None)
if ishtml:
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title: headers['Title'] = parser.title
if bodyfound:
text = self.text = bodyfound.group('bodycontent')
text_format = self.text_format = 'html'
else:
headers, text = parseHeadersBody(text, headers)
text_format = self.text_format = 'structured-text'
self.text = text
headers['Format'] = self.Format()
haveheader = headers.has_key
for key, value in self.getMetadataHeaders():
if key != 'Format' and not haveheader(key):
headers[key] = value
self.editMetadata(
title=headers['Title'],
subject=headers['Subject'],
description=headers['Description'],
contributors=headers['Contributors'],
effective_date=headers['Effective_date'],
expiration_date=headers['Expiration_date'],
format=headers['Format'],
language=headers['Language'],
rights=headers['Rights'],
)
self._parse()
def edit(self, text_format, text, file=''):
"""
Edit the Document
"""
self.text = text
headers = {}
if file and (type(file) is not type('')):
contents=file.read()
if contents:
text = self.text = contents
# Now parse out HTML if its applicable, or the plain text,
# getting any headers passed along in the document
bodyfound = bodyfinder.search(text)
ishtml = (text_format == 'html') or (bodyfound is not None)
if ishtml:
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title: headers['Title'] = parser.title
if bodyfound:
text = self.text = bodyfound.group('bodycontent')
text_format = self.text_format = 'html'
else:
headers, text = parseHeadersBody(text, headers)
text_format = self.text_format = 'structured-text'
self.text = text
headers['Format'] = self.Format()
haveheader = headers.has_key
for key, value in self.getMetadataHeaders():
if key != 'Format' and not haveheader(key):
headers[key] = value
self.editMetadata(title=headers['Title'],
subject=headers['Subject'],
description=headers['Description'],
contributors=headers['Contributors'],
effective_date=headers['Effective_date'],
expiration_date=headers['Expiration_date'],
format=headers['Format'],
language=headers['Language'],
rights=headers['Rights'],
)
self._parse()
def handleText(self, text, format=None):
""" Handles the raw text, returning headers, body, cooked, format """
headers = {}
body = cooked = text
if not format:
format = self.guessFormat(text)
if format == 'html':
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title:
headers['Title'] = parser.title
bodyfound = bodyfinder.search(text)
if bodyfound:
cooked = body = bodyfound.group('bodycontent')
else:
headers, body = parseHeadersBody(text, headers)
cooked = _format_stx(text=body)
return headers, body, cooked, format
def handleText(self, text, format=None):
""" Handles the raw text, returning headers, body, cooked, format """
headers = {}
body = cooked = text
if not format:
format = self.guessFormat(text)
if format == 'html':
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title:
headers['Title'] = parser.title
bodyfound = bodyfinder.search(text)
if bodyfound:
cooked = body = bodyfound.group('bodycontent')
else:
headers, body = parseHeadersBody(text, headers)
cooked = _format_stx(text=body)
return headers, body, cooked, format
def handleText(self, text, format=None, stx_level=None):
""" Handles the raw text, returning headers, body, cooked, format """
headers = {}
body = cooked = text
level = stx_level or self._stx_level
if not format:
format = self.guessFormat(text)
if format == 'html':
parser = SimpleHTMLParser()
parser.feed(text)
headers.update(parser.metatags)
if parser.title:
headers['Title'] = parser.title
bodyfound = bodyfinder(text)
if bodyfound:
cooked = body = bodyfound
else:
headers, body = parseHeadersBody(text, headers)
cooked = _format_stx(text=body, level=level)
self._stx_level = level
return headers, body, cooked, format