mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-26 18:29:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

Convert to using string methods instead of the string module.

Browse source 
In goahead(), use a bound version of rawdata.startswith() since we use the
same method all the time and never change the value of rawdata.  This can
save a lot of bound method creation.
This commit is contained in:
Fred Drake 2001-12-03 17:09:50 +00:00
parent 073148c4ef
commit 248b04383f
1 changed files with 25 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

54
Lib/HTMLParser.py
View file

@ -10,7 +10,6 @@
import markupbase import markupbase
import re import re
import string
# Regular expressions used for parsing # Regular expressions used for parsing
@ -23,7 +22,6 @@ charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen = re.compile('<[a-zA-Z]') starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>') piclose = re.compile('>')
endtagopen = re.compile('</')
commentclose = re.compile(r'--\s*>') commentclose = re.compile(r'--\s*>')
tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
attrfind = re.compile( attrfind = re.compile(
@ -96,7 +94,6 @@ class HTMLParser(markupbase.ParserBase):
def reset(self): def reset(self):
"""Reset this instance. Loses all unprocessed data.""" """Reset this instance. Loses all unprocessed data."""
self.rawdata = '' self.rawdata = ''
self.stack = []
self.lasttag = '???' self.lasttag = '???'
self.interesting = interesting_normal self.interesting = interesting_normal
markupbase.ParserBase.reset(self) markupbase.ParserBase.reset(self)
@ -145,18 +142,19 @@ class HTMLParser(markupbase.ParserBase):
if i < j: self.handle_data(rawdata[i:j]) if i < j: self.handle_data(rawdata[i:j])
i = self.updatepos(i, j) i = self.updatepos(i, j)
if i == n: break if i == n: break
if rawdata[i] == '<': startswith = rawdata.startswith
if startswith('<', i):
if starttagopen.match(rawdata, i): # < + letter if starttagopen.match(rawdata, i): # < + letter
k = self.parse_starttag(i) k = self.parse_starttag(i)
elif endtagopen.match(rawdata, i): # </ elif startswith("</", i):
k = self.parse_endtag(i) k = self.parse_endtag(i)
if k >= 0: if k >= 0:
self.clear_cdata_mode() self.clear_cdata_mode()
elif rawdata.startswith("<!--", i): # <!-- elif startswith("<!--", i):
k = self.parse_comment(i) k = self.parse_comment(i)
elif rawdata.startswith("<?", i): # <? elif startswith("<?", i):
k = self.parse_pi(i) k = self.parse_pi(i)
elif rawdata.startswith("<!", i): # <! elif startswith("<!", i):
k = self.parse_declaration(i) k = self.parse_declaration(i)
elif (i + 1) < n: elif (i + 1) < n:
self.handle_data("<") self.handle_data("<")
@ -168,33 +166,32 @@ class HTMLParser(markupbase.ParserBase):
self.error("EOF in middle of construct") self.error("EOF in middle of construct")
break break
i = self.updatepos(i, k) i = self.updatepos(i, k)
elif rawdata[i:i+2] == "&#": elif startswith("&#", i):
match = charref.match(rawdata, i) match = charref.match(rawdata, i)
if match: if match:
name = match.group()[2:-1] name = match.group()[2:-1]
self.handle_charref(name) self.handle_charref(name)
k = match.end() k = match.end()
if rawdata[k-1] != ';': if not startswith(';', k-1):
k = k - 1 k = k - 1
i = self.updatepos(i, k) i = self.updatepos(i, k)
continue continue
else: else:
break break
elif rawdata[i] == '&': elif startswith('&', i):
match = entityref.match(rawdata, i) match = entityref.match(rawdata, i)
if match: if match:
name = match.group(1) name = match.group(1)
self.handle_entityref(name) self.handle_entityref(name)
k = match.end() k = match.end()
if rawdata[k-1] != ';': if not startswith(';', k-1):
k = k - 1 k = k - 1
i = self.updatepos(i, k) i = self.updatepos(i, k)
continue continue
match = incomplete.match(rawdata, i) match = incomplete.match(rawdata, i)
if match: if match:
# match.group() will contain at least 2 chars # match.group() will contain at least 2 chars
rest = rawdata[i:] if end and match.group() == rawdata[i:]:
if end and match.group() == rest:
self.error("EOF in middle of entity or char ref") self.error("EOF in middle of entity or char ref")
# incomplete # incomplete
break break
@ -252,7 +249,7 @@ class HTMLParser(markupbase.ParserBase):
match = tagfind.match(rawdata, i+1) match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()' assert match, 'unexpected call to parse_starttag()'
k = match.end() k = match.end()
self.lasttag = tag = string.lower(rawdata[i+1:k]) self.lasttag = tag = rawdata[i+1:k].lower()
while k < endpos: while k < endpos:
m = attrfind.match(rawdata, k) m = attrfind.match(rawdata, k)
@ -265,21 +262,21 @@ class HTMLParser(markupbase.ParserBase):
attrvalue[:1] == '"' == attrvalue[-1:]: attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1] attrvalue = attrvalue[1:-1]
attrvalue = self.unescape(attrvalue) attrvalue = self.unescape(attrvalue)
attrs.append((string.lower(attrname), attrvalue)) attrs.append((attrname.lower(), attrvalue))
k = m.end() k = m.end()
end = string.strip(rawdata[k:endpos]) end = rawdata[k:endpos].strip()
if end not in (">", "/>"): if end not in (">", "/>"):
lineno, offset = self.getpos() lineno, offset = self.getpos()
if "\n" in self.__starttag_text: if "\n" in self.__starttag_text:
lineno = lineno + string.count(self.__starttag_text, "\n") lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \ offset = len(self.__starttag_text) \
- string.rfind(self.__starttag_text, "\n") - self.__starttag_text.rfind("\n")
else: else:
offset = offset + len(self.__starttag_text) offset = offset + len(self.__starttag_text)
self.error("junk characters in start tag: %s" self.error("junk characters in start tag: %s"
% `rawdata[k:endpos][:20]`) % `rawdata[k:endpos][:20]`)
if end[-2:] == '/>': if end.endswith('/>'):
# XHTML-style empty tag: <span attr="value" /> # XHTML-style empty tag: <span attr="value" />
self.handle_startendtag(tag, attrs) self.handle_startendtag(tag, attrs)
else: else:
@ -299,10 +296,9 @@ class HTMLParser(markupbase.ParserBase):
if next == ">": if next == ">":
return j + 1 return j + 1
if next == "/": if next == "/":
s = rawdata[j:j+2] if rawdata.startswith("/>", j):
if s == "/>":
return j + 2 return j + 2
if s == "/": if rawdata.startswith("/", j):
# buffer boundary # buffer boundary
return -1 return -1
# else bogus input # else bogus input
@ -332,7 +328,7 @@ class HTMLParser(markupbase.ParserBase):
if not match: if not match:
self.error("bad end tag: %s" % `rawdata[i:j]`) self.error("bad end tag: %s" % `rawdata[i:j]`)
tag = match.group(1) tag = match.group(1)
self.handle_endtag(string.lower(tag)) self.handle_endtag(tag.lower())
return j return j
# Overridable -- finish processing of start+end tag: <tag.../> # Overridable -- finish processing of start+end tag: <tag.../>
@ -379,9 +375,9 @@ class HTMLParser(markupbase.ParserBase):
def unescape(self, s): def unescape(self, s):
if '&' not in s: if '&' not in s:
return s return s
s = string.replace(s, "&lt;", "<") s = s.replace("&lt;", "<")
s = string.replace(s, "&gt;", ">") s = s.replace("&gt;", ">")
s = string.replace(s, "&apos;", "'") s = s.replace("&apos;", "'")
s = string.replace(s, "&quot;", '"') s = s.replace("&quot;", '"')
s = string.replace(s, "&amp;", "&") # Must be last s = s.replace("&amp;", "&") # Must be last
return s return s