Changeset 388 for python/vendor/current/Lib/HTMLParser.py

Timestamp:

Mar 19, 2014, 11:11:30 AM (11 years ago)

Author:

dmik

Message:

python: Update vendor to 2.7.6.

File:

• python/vendor/current/Lib/HTMLParser.py (modified) (17 diffs)

python/vendor/current/Lib/HTMLParser.py

@@ -15 +15 @@
 
 interesting_normal = re.compile('[&<]')
-interesting_cdata = re.compile(r'<(/|\Z)')
 incomplete = re.compile('&[a-zA-Z#]')
 
@@ -24 +23 @@
 piclose = re.compile('>')
 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:_]*)(?:\s|/(?!>))*')
+# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
+# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
+tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
+
 attrfind = re.compile(
-    r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
-    r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?')
+    r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
+    r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
 
 locatestarttagend = re.compile(r"""
   <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
-  (?:\s+                             # whitespace before attribute name
-    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
-      (?:\s*=\s*                     # value indicator
+  (?:[\s/]*                          # optional whitespace before attribute name
+    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
+      (?:\s*=+\s*                    # value indicator
         (?:'[^']*'                   # LITA-enclosed value
-          |\"[^\"]*\"                # LIT-enclosed value
-          |[^'\">\s]+                # bare value
+          |"[^"]*"                   # LIT-enclosed value
+          |(?!['"])[^>\s]*           # bare value
          )
-       )?
-     )
-   )*
+       )?(?:\s|/(?!>))*
+     )*
+   )?
   \s*                                # trailing whitespace
 """, re.VERBOSE)
 endendtag = re.compile('>')
+# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
+# </ and the tag name, so maybe this should be fixed
 endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
 
@@ -97 +102 @@
         self.lasttag = '???'
         self.interesting = interesting_normal
+        self.cdata_elem = None
         markupbase.ParserBase.reset(self)
 
     def feed(self, data):
-        """Feed data to the parser.
+        r"""Feed data to the parser.
 
         Call this as often as you want, with as little or as much text
@@ -121 +127 @@
         return self.__starttag_text
 
-    def set_cdata_mode(self):
-        self.interesting = interesting_cdata
+    def set_cdata_mode(self, elem):
+        self.cdata_elem = elem.lower()
+        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
 
     def clear_cdata_mode(self):
         self.interesting = interesting_normal
+        self.cdata_elem = None
 
     # Internal -- handle data as far as reasonable.  May leave state
@@ -139 +147 @@
                 j = match.start()
             else:
+                if self.cdata_elem:
+                    break
                 j = n
             if i < j: self.handle_data(rawdata[i:j])
@@ -154 +164 @@
                     k = self.parse_pi(i)
                 elif startswith("<!", i):
-                    k = self.parse_declaration(i)
+                    k = self.parse_html_declaration(i)
                 elif (i + 1) < n:
                     self.handle_data("<")
@@ -161 +171 @@
                     break
                 if k < 0:
-                    if end:
-                        self.error("EOF in middle of construct")
-                    break
+                    if not end:
+                        break
+                    k = rawdata.find('>', i + 1)
+                    if k < 0:
+                        k = rawdata.find('<', i + 1)
+                        if k < 0:
+                            k = i + 1
+                    else:
+                        k += 1
+                    self.handle_data(rawdata[i:k])
                 i = self.updatepos(i, k)
             elif startswith("&#", i):
@@ -176 +193 @@
                     continue
                 else:
+                    if ";" in rawdata[i:]: #bail by consuming &#
+                        self.handle_data(rawdata[0:2])
+                        i = self.updatepos(i, 2)
                     break
             elif startswith('&', i):
@@ -204 +224 @@
                 assert 0, "interesting.search() lied"
         # end while
-        if end and i < n:
+        if end and i < n and not self.cdata_elem:
             self.handle_data(rawdata[i:n])
             i = self.updatepos(i, n)
         self.rawdata = rawdata[i:]
+
+    # Internal -- parse html declarations, return length or -1 if not terminated
+    # See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
+    # See also parse_declaration in _markupbase
+    def parse_html_declaration(self, i):
+        rawdata = self.rawdata
+        if rawdata[i:i+2] != '<!':
+            self.error('unexpected call to parse_html_declaration()')
+        if rawdata[i:i+4] == '<!--':
+            # this case is actually already handled in goahead()
+            return self.parse_comment(i)
+        elif rawdata[i:i+3] == '<![':
+            return self.parse_marked_section(i)
+        elif rawdata[i:i+9].lower() == '<!doctype':
+            # find the closing >
+            gtpos = rawdata.find('>', i+9)
+            if gtpos == -1:
+                return -1
+            self.handle_decl(rawdata[i+2:gtpos])
+            return gtpos+1
+        else:
+            return self.parse_bogus_comment(i)
+
+    # Internal -- parse bogus comment, return length or -1 if not terminated
+    # see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
+    def parse_bogus_comment(self, i, report=1):
+        rawdata = self.rawdata
+        if rawdata[i:i+2] not in ('<!', '</'):
+            self.error('unexpected call to parse_comment()')
+        pos = rawdata.find('>', i+2)
+        if pos == -1:
+            return -1
+        if report:
+            self.handle_comment(rawdata[i+2:pos])
+        return pos + 1
 
     # Internal -- parse processing instr, return end or -1 if not terminated
@@ -235 +290 @@
         assert match, 'unexpected call to parse_starttag()'
         k = match.end()
-        self.lasttag = tag = rawdata[i+1:k].lower()
+        self.lasttag = tag = match.group(1).lower()
 
         while k < endpos:
@@ -247 +302 @@
                  attrvalue[:1] == '"' == attrvalue[-1:]:
                 attrvalue = attrvalue[1:-1]
+            if attrvalue:
                 attrvalue = self.unescape(attrvalue)
             attrs.append((attrname.lower(), attrvalue))
@@ -260 +316 @@
             else:
                 offset = offset + len(self.__starttag_text)
-            self.error("junk characters in start tag: %r"
-                       % (rawdata[k:endpos][:20],))
+            self.handle_data(rawdata[i:endpos])
+            return endpos
         if end.endswith('/>'):
             # XHTML-style empty tag: <span attr="value" />
@@ -268 +324 @@
             self.handle_starttag(tag, attrs)
             if tag in self.CDATA_CONTENT_ELEMENTS:
-                self.set_cdata_mode()
+                self.set_cdata_mode(tag)
         return endpos
 
@@ -298 +354 @@
                 # '/' from a '/>' ending
                 return -1
-            self.updatepos(i, j)
-            self.error("malformed start tag")
+            if j > i:
+                return j
+            else:
+                return i + 1
         raise AssertionError("we should not get here!")
 
@@ -309 +367 @@
         if not match:
             return -1
-        j = match.end()
+        gtpos = match.end()
         match = endtagfind.match(rawdata, i) # </ + tag + >
         if not match:
-            self.error("bad end tag: %r" % (rawdata[i:j],))
-        tag = match.group(1)
-        self.handle_endtag(tag.lower())
+            if self.cdata_elem is not None:
+                self.handle_data(rawdata[i:gtpos])
+                return gtpos
+            # find the name: w3.org/TR/html5/tokenization.html#tag-name-state
+            namematch = tagfind_tolerant.match(rawdata, i+2)
+            if not namematch:
+                # w3.org/TR/html5/tokenization.html#end-tag-open-state
+                if rawdata[i:i+3] == '</>':
+                    return i+3
+                else:
+                    return self.parse_bogus_comment(i)
+            tagname = namematch.group().lower()
+            # consume and ignore other stuff between the name and the >
+            # Note: this is not 100% correct, since we might have things like
+            # </tag attr=">">, but looking for > after tha name should cover
+            # most of the cases and is much simpler
+            gtpos = rawdata.find('>', namematch.end())
+            self.handle_endtag(tagname)
+            return gtpos+1
+
+        elem = match.group(1).lower() # script or style
+        if self.cdata_elem is not None:
+            if elem != self.cdata_elem:
+                self.handle_data(rawdata[i:gtpos])
+                return gtpos
+
+        self.handle_endtag(elem)
         self.clear_cdata_mode()
-        return j
+        return gtpos
 
     # Overridable -- finish processing of start+end tag: <tag.../>
@@ -356 +438 @@
 
     def unknown_decl(self, data):
-        self.error("unknown declaration: %r" % (data,))
+        pass
 
     # Internal -- helper to remove special character quoting
@@ -365 +447 @@
         def replaceEntities(s):
             s = s.groups()[0]
-            if s[0] == "#":
-                s = s[1:]
-                if s[0] in ['x','X']:
-                    c = int(s[1:], 16)
-                else:
-                    c = int(s)
-                return unichr(c)
+            try:
+                if s[0] == "#":
+                    s = s[1:]
+                    if s[0] in ['x','X']:
+                        c = int(s[1:], 16)
+                    else:
+                        c = int(s)
+                    return unichr(c)
+            except ValueError:
+                return '&#'+s+';'
             else:
                 # Cannot use name2codepoint directly, because HTMLParser supports apos,