Restores compatibility with Python >=3.9,
which removed the custom .error() method in
https://github.com/python/cpython/commit/e34bbfd61f405eef89e8aa50672b0b25022de320
Despite the big diff, only a try…except clause is added.
--- source/sgmllib.py 2023-03-18 08:57:58.726240606 +0100
+++ source/sgmllib.py 2023-03-18 09:02:01.667568916 +0100
@@ -101,113 +101,116 @@
"""Handle the remaining data."""
self.goahead(1)
- def error(self, message):
- raise SGMLParseError(message)
-
# Internal -- handle data as far as reasonable. May leave state
# and data to be processed by a subsequent call. If 'end' is
# true, force handling all data as if followed by EOF marker.
def goahead(self, end):
- rawdata = self.rawdata
- i = 0
- n = len(rawdata)
- while i < n:
- if self.nomoretags:
- self.handle_data(rawdata[i:n])
- i = n
- break
- match = interesting.search(rawdata, i)
- if match: j = match.start()
- else: j = n
- if i < j:
- self.handle_data(rawdata[i:j])
- i = j
- if i == n: break
- if rawdata[i] == '<':
- if starttagopen.match(rawdata, i):
+ try:
+ rawdata = self.rawdata
+ i = 0
+ n = len(rawdata)
+ while i < n:
+ if self.nomoretags:
+ self.handle_data(rawdata[i:n])
+ i = n
+ break
+ match = interesting.search(rawdata, i)
+ if match: j = match.start()
+ else: j = n
+ if i < j:
+ self.handle_data(rawdata[i:j])
+ i = j
+ if i == n: break
+ if rawdata[i] == '<':
+ if starttagopen.match(rawdata, i):
+ if self.literal:
+ self.handle_data(rawdata[i])
+ i = i+1
+ continue
+ k = self.parse_starttag(i)
+ if k < 0: break
+ i = k
+ continue
+ if rawdata.startswith("</", i):
+ k = self.parse_endtag(i)
+ if k < 0: break
+ i = k
+ self.literal = 0
+ continue
+ if self.literal:
+ if n > (i + 1):
+ self.handle_data("<")
+ i = i+1
+ else:
+ # incomplete
+ break
+ continue
+ if rawdata.startswith("<!--", i):
+ # Strictly speaking, a comment is --.*--
+ # within a declaration tag <!...>.
+ # This should be removed,
+ # and comments handled only in parse_declaration.
+ k = self.parse_comment(i)
+ if k < 0: break
+ i = k
+ continue
+ if rawdata.startswith("<?", i):
+ k = self.parse_pi(i)
+ if k < 0: break
+ i = i+k
+ continue
+ if rawdata.startswith("<!", i):
+ # This is some sort of declaration; in "HTML as
+ # deployed," this should only be the document type
+ # declaration ("<!DOCTYPE html...>").
+ k = self.parse_declaration(i)
+ if k < 0: break
+ i = k
+ continue
+ elif rawdata[i] == '&':
if self.literal:
self.handle_data(rawdata[i])
i = i+1
continue
- k = self.parse_starttag(i)
- if k < 0: break
- i = k
- continue
- if rawdata.startswith("</", i):
- k = self.parse_endtag(i)
- if k < 0: break
- i = k
- self.literal = 0
- continue
- if self.literal:
- if n > (i + 1):
- self.handle_data("<")
- i = i+1
- else:
- # incomplete
- break
- continue
- if rawdata.startswith("<!--", i):
- # Strictly speaking, a comment is --.*--
- # within a declaration tag <!...>.
- # This should be removed,
- # and comments handled only in parse_declaration.
- k = self.parse_comment(i)
- if k < 0: break
- i = k
- continue
- if rawdata.startswith("<?", i):
- k = self.parse_pi(i)
- if k < 0: break
- i = i+k
- continue
- if rawdata.startswith("<!", i):
- # This is some sort of declaration; in "HTML as
- # deployed," this should only be the document type
- # declaration ("<!DOCTYPE html...>").
- k = self.parse_declaration(i)
- if k < 0: break
- i = k
- continue
- elif rawdata[i] == '&':
- if self.literal:
+ match = charref.match(rawdata, i)
+ if match:
+ name = match.group(1)
+ self.handle_charref(name)
+ i = match.end(0)
+ if rawdata[i-1] != ';': i = i-1
+ continue
+ match = entityref.match(rawdata, i)
+ if match:
+ name = match.group(1)
+ self.handle_entityref(name)
+ i = match.end(0)
+ if rawdata[i-1] != ';': i = i-1
+ continue
+ else:
+ self.error('neither < nor & ??')
+ # We get here only if incomplete matches but
+ # nothing else
+ match = incomplete.match(rawdata, i)
+ if not match:
self.handle_data(rawdata[i])
i = i+1
continue
- match = charref.match(rawdata, i)
- if match:
- name = match.group(1)
- self.handle_charref(name)
- i = match.end(0)
- if rawdata[i-1] != ';': i = i-1
- continue
- match = entityref.match(rawdata, i)
- if match:
- name = match.group(1)
- self.handle_entityref(name)
- i = match.end(0)
- if rawdata[i-1] != ';': i = i-1
- continue
- else:
- self.error('neither < nor & ??')
- # We get here only if incomplete matches but
- # nothing else
- match = incomplete.match(rawdata, i)
- if not match:
- self.handle_data(rawdata[i])
- i = i+1
- continue
- j = match.end(0)
- if j == n:
- break # Really incomplete
- self.handle_data(rawdata[i:j])
- i = j
- # end while
- if end and i < n:
- self.handle_data(rawdata[i:n])
- i = n
- self.rawdata = rawdata[i:]
- # XXX if end: check for empty stack
+ j = match.end(0)
+ if j == n:
+ break # Really incomplete
+ self.handle_data(rawdata[i:j])
+ i = j
+ # end while
+ if end and i < n:
+ self.handle_data(rawdata[i:n])
+ i = n
+ self.rawdata = rawdata[i:]
+ # XXX if end: check for empty stack
+ except AssertionError as e:
+ # The .error() method, which threw the custom SGMLParseError was removed
+ # by https://github.com/python/cpython/issues/76025. So we have to catch
+ # _markupbase’s AssertionError and translate it into the old one.
+ raise SGMLParseError (e.args[0]) from e
# Extensions for the DOCTYPE scanner:
_decl_otherchars = '='
