rubyfox-server 2.3.0.pre2

data/lib/rubyfox/server/data/lib/Lib/mailcap.py

@@ -0,0 +1,255 @@
+"""Mailcap file handling.  See RFC 1524."""
+
+import os
+
+__all__ = ["getcaps","findmatch"]
+
+# Part 1: top-level interface.
+
+def getcaps():
+    """Return a dictionary containing the mailcap database.
+
+    The dictionary maps a MIME type (in all lowercase, e.g. 'text/plain')
+    to a list of dictionaries corresponding to mailcap entries.  The list
+    collects all the entries for that MIME type from all available mailcap
+    files.  Each dictionary contains key-value pairs for that MIME type,
+    where the viewing command is stored with the key "view".
+
+    """
+    caps = {}
+    for mailcap in listmailcapfiles():
+        try:
+            fp = open(mailcap, 'r')
+        except IOError:
+            continue
+        morecaps = readmailcapfile(fp)
+        fp.close()
+        for key in morecaps.keys():
+            if not caps.has_key(key):
+                caps[key] = morecaps[key]
+            else:
+                caps[key] = caps[key] + morecaps[key]
+    return caps
+
+def listmailcapfiles():
+    """Return a list of all mailcap files found on the system."""
+    # XXX Actually, this is Unix-specific
+    if os.environ.has_key('MAILCAPS'):
+        str = os.environ['MAILCAPS']
+        mailcaps = str.split(':')
+    else:
+        if os.environ.has_key('HOME'):
+            home = os.environ['HOME']
+        else:
+            # Don't bother with getpwuid()
+            home = '.' # Last resort
+        mailcaps = [home + '/.mailcap', '/etc/mailcap',
+                '/usr/etc/mailcap', '/usr/local/etc/mailcap']
+    return mailcaps
+
+
+# Part 2: the parser.
+
+def readmailcapfile(fp):
+    """Read a mailcap file and return a dictionary keyed by MIME type.
+
+    Each MIME type is mapped to an entry consisting of a list of
+    dictionaries; the list will contain more than one such dictionary
+    if a given MIME type appears more than once in the mailcap file.
+    Each dictionary contains key-value pairs for that MIME type, where
+    the viewing command is stored with the key "view".
+    """
+    caps = {}
+    while 1:
+        line = fp.readline()
+        if not line: break
+        # Ignore comments and blank lines
+        if line[0] == '#' or line.strip() == '':
+            continue
+        nextline = line
+        # Join continuation lines
+        while nextline[-2:] == '\\\n':
+            nextline = fp.readline()
+            if not nextline: nextline = '\n'
+            line = line[:-2] + nextline
+        # Parse the line
+        key, fields = parseline(line)
+        if not (key and fields):
+            continue
+        # Normalize the key
+        types = key.split('/')
+        for j in range(len(types)):
+            types[j] = types[j].strip()
+        key = '/'.join(types).lower()
+        # Update the database
+        if caps.has_key(key):
+            caps[key].append(fields)
+        else:
+            caps[key] = [fields]
+    return caps
+
+def parseline(line):
+    """Parse one entry in a mailcap file and return a dictionary.
+
+    The viewing command is stored as the value with the key "view",
+    and the rest of the fields produce key-value pairs in the dict.
+    """
+    fields = []
+    i, n = 0, len(line)
+    while i < n:
+        field, i = parsefield(line, i, n)
+        fields.append(field)
+        i = i+1 # Skip semicolon
+    if len(fields) < 2:
+        return None, None
+    key, view, rest = fields[0], fields[1], fields[2:]
+    fields = {'view': view}
+    for field in rest:
+        i = field.find('=')
+        if i < 0:
+            fkey = field
+            fvalue = ""
+        else:
+            fkey = field[:i].strip()
+            fvalue = field[i+1:].strip()
+        if fields.has_key(fkey):
+            # Ignore it
+            pass
+        else:
+            fields[fkey] = fvalue
+    return key, fields
+
+def parsefield(line, i, n):
+    """Separate one key-value pair in a mailcap entry."""
+    start = i
+    while i < n:
+        c = line[i]
+        if c == ';':
+            break
+        elif c == '\\':
+            i = i+2
+        else:
+            i = i+1
+    return line[start:i].strip(), i
+
+
+# Part 3: using the database.
+
+def findmatch(caps, MIMEtype, key='view', filename="/dev/null", plist=[]):
+    """Find a match for a mailcap entry.
+
+    Return a tuple containing the command line, and the mailcap entry
+    used; (None, None) if no match is found.  This may invoke the
+    'test' command of several matching entries before deciding which
+    entry to use.
+
+    """
+    entries = lookup(caps, MIMEtype, key)
+    # XXX This code should somehow check for the needsterminal flag.
+    for e in entries:
+        if e.has_key('test'):
+            test = subst(e['test'], filename, plist)
+            if test and os.system(test) != 0:
+                continue
+        command = subst(e[key], MIMEtype, filename, plist)
+        return command, e
+    return None, None
+
+def lookup(caps, MIMEtype, key=None):
+    entries = []
+    if caps.has_key(MIMEtype):
+        entries = entries + caps[MIMEtype]
+    MIMEtypes = MIMEtype.split('/')
+    MIMEtype = MIMEtypes[0] + '/*'
+    if caps.has_key(MIMEtype):
+        entries = entries + caps[MIMEtype]
+    if key is not None:
+        entries = filter(lambda e, key=key: e.has_key(key), entries)
+    return entries
+
+def subst(field, MIMEtype, filename, plist=[]):
+    # XXX Actually, this is Unix-specific
+    res = ''
+    i, n = 0, len(field)
+    while i < n:
+        c = field[i]; i = i+1
+        if c != '%':
+            if c == '\\':
+                c = field[i:i+1]; i = i+1
+            res = res + c
+        else:
+            c = field[i]; i = i+1
+            if c == '%':
+                res = res + c
+            elif c == 's':
+                res = res + filename
+            elif c == 't':
+                res = res + MIMEtype
+            elif c == '{':
+                start = i
+                while i < n and field[i] != '}':
+                    i = i+1
+                name = field[start:i]
+                i = i+1
+                res = res + findparam(name, plist)
+            # XXX To do:
+            # %n == number of parts if type is multipart/*
+            # %F == list of alternating type and filename for parts
+            else:
+                res = res + '%' + c
+    return res
+
+def findparam(name, plist):
+    name = name.lower() + '='
+    n = len(name)
+    for p in plist:
+        if p[:n].lower() == name:
+            return p[n:]
+    return ''
+
+
+# Part 4: test program.
+
+def test():
+    import sys
+    caps = getcaps()
+    if not sys.argv[1:]:
+        show(caps)
+        return
+    for i in range(1, len(sys.argv), 2):
+        args = sys.argv[i:i+2]
+        if len(args) < 2:
+            print "usage: mailcap [MIMEtype file] ..."
+            return
+        MIMEtype = args[0]
+        file = args[1]
+        command, e = findmatch(caps, MIMEtype, 'view', file)
+        if not command:
+            print "No viewer found for", type
+        else:
+            print "Executing:", command
+            sts = os.system(command)
+            if sts:
+                print "Exit status:", sts
+
+def show(caps):
+    print "Mailcap files:"
+    for fn in listmailcapfiles(): print "\t" + fn
+    print
+    if not caps: caps = getcaps()
+    print "Mailcap entries:"
+    print
+    ckeys = caps.keys()
+    ckeys.sort()
+    for type in ckeys:
+        print type
+        entries = caps[type]
+        for e in entries:
+            keys = e.keys()
+            keys.sort()
+            for k in keys:
+                print "  %-15s" % k, e[k]
+            print
+
+if __name__ == '__main__':
+    test()

data/lib/rubyfox/server/data/lib/Lib/markupbase.py

@@ -0,0 +1,317 @@
+"""Shared support for scanning document type declarations in HTML and XHTML."""
+
+import re
+import string
+
+_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
+_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
+
+del re
+
+
+class ParserBase:
+    """Parser base class which provides some common support methods used
+    by the SGML/HTML and XHTML parsers."""
+
+    def __init__(self):
+        if self.__class__ is ParserBase:
+            raise RuntimeError(
+                "markupbase.ParserBase must be subclassed")
+
+    def error(self, message):
+        raise NotImplementedError(
+            "subclasses of ParserBase must override error()")
+
+    def reset(self):
+        self.lineno = 1
+        self.offset = 0
+
+    def getpos(self):
+        """Return current line number and offset."""
+        return self.lineno, self.offset
+
+    # Internal -- update line number and offset.  This should be
+    # called for each piece of data exactly once, in order -- in other
+    # words the concatenation of all the input strings to this
+    # function should be exactly the entire input.
+    def updatepos(self, i, j):
+        if i >= j:
+            return j
+        rawdata = self.rawdata
+        nlines = string.count(rawdata, "\n", i, j)
+        if nlines:
+            self.lineno = self.lineno + nlines
+            pos = string.rindex(rawdata, "\n", i, j) # Should not fail
+            self.offset = j-(pos+1)
+        else:
+            self.offset = self.offset + j-i
+        return j
+
+    _decl_otherchars = ''
+
+    # Internal -- parse declaration (for use by subclasses).
+    def parse_declaration(self, i):
+        # This is some sort of declaration; in "HTML as
+        # deployed," this should only be the document type
+        # declaration ("<!DOCTYPE html...>").
+        rawdata = self.rawdata
+        j = i + 2
+        assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
+        if rawdata[j:j+1] in ("-", ""):
+            # Start of comment followed by buffer boundary,
+            # or just a buffer boundary.
+            return -1
+        # in practice, this should look like: ((name|stringlit) S*)+ '>'
+        n = len(rawdata)
+        decltype, j = self._scan_name(j, i)
+        if j < 0:
+            return j
+        if decltype == "doctype":
+            self._decl_otherchars = ''
+        while j < n:
+            c = rawdata[j]
+            if c == ">":
+                # end of declaration syntax
+                data = rawdata[i+2:j]
+                if decltype == "doctype":
+                    self.handle_decl(data)
+                else:
+                    self.unknown_decl(data)
+                return j + 1
+            if c in "\"'":
+                m = _declstringlit_match(rawdata, j)
+                if not m:
+                    return -1 # incomplete
+                j = m.end()
+            elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
+                name, j = self._scan_name(j, i)
+            elif c in self._decl_otherchars:
+                j = j + 1
+            elif c == "[":
+                if decltype == "doctype":
+                    j = self._parse_doctype_subset(j + 1, i)
+                else:
+                    self.error("unexpected '[' char in declaration")
+            else:
+                self.error(
+                    "unexpected %s char in declaration" % `rawdata[j]`)
+            if j < 0:
+                return j
+        return -1 # incomplete
+
+    # Internal -- scan past the internal subset in a <!DOCTYPE declaration,
+    # returning the index just past any whitespace following the trailing ']'.
+    def _parse_doctype_subset(self, i, declstartpos):
+        rawdata = self.rawdata
+        n = len(rawdata)
+        j = i
+        while j < n:
+            c = rawdata[j]
+            if c == "<":
+                s = rawdata[j:j+2]
+                if s == "<":
+                    # end of buffer; incomplete
+                    return -1
+                if s != "<!":
+                    self.updatepos(declstartpos, j + 1)
+                    self.error("unexpected char in internal subset (in %s)"
+                               % `s`)
+                if (j + 2) == n:
+                    # end of buffer; incomplete
+                    return -1
+                if (j + 4) > n:
+                    # end of buffer; incomplete
+                    return -1
+                if rawdata[j:j+4] == "<!--":
+                    j = self.parse_comment(j, report=0)
+                    if j < 0:
+                        return j
+                    continue
+                name, j = self._scan_name(j + 2, declstartpos)
+                if j == -1:
+                    return -1
+                if name not in ("attlist", "element", "entity", "notation"):
+                    self.updatepos(declstartpos, j + 2)
+                    self.error(
+                        "unknown declaration %s in internal subset" % `name`)
+                # handle the individual names
+                meth = getattr(self, "_parse_doctype_" + name)
+                j = meth(j, declstartpos)
+                if j < 0:
+                    return j
+            elif c == "%":
+                # parameter entity reference
+                if (j + 1) == n:
+                    # end of buffer; incomplete
+                    return -1
+                s, j = self._scan_name(j + 1, declstartpos)
+                if j < 0:
+                    return j
+                if rawdata[j] == ";":
+                    j = j + 1
+            elif c == "]":
+                j = j + 1
+                while j < n and rawdata[j] in string.whitespace:
+                    j = j + 1
+                if j < n:
+                    if rawdata[j] == ">":
+                        return j
+                    self.updatepos(declstartpos, j)
+                    self.error("unexpected char after internal subset")
+                else:
+                    return -1
+            elif c in string.whitespace:
+                j = j + 1
+            else:
+                self.updatepos(declstartpos, j)
+                self.error("unexpected char %s in internal subset" % `c`)
+        # end of buffer reached
+        return -1
+
+    # Internal -- scan past <!ELEMENT declarations
+    def _parse_doctype_element(self, i, declstartpos):
+        name, j = self._scan_name(i, declstartpos)
+        if j == -1:
+            return -1
+        # style content model; just skip until '>'
+        rawdata = self.rawdata
+        if '>' in rawdata[j:]:
+            return string.find(rawdata, ">", j) + 1
+        return -1
+
+    # Internal -- scan past <!ATTLIST declarations
+    def _parse_doctype_attlist(self, i, declstartpos):
+        rawdata = self.rawdata
+        name, j = self._scan_name(i, declstartpos)
+        c = rawdata[j:j+1]
+        if c == "":
+            return -1
+        if c == ">":
+            return j + 1
+        while 1:
+            # scan a series of attribute descriptions; simplified:
+            #   name type [value] [#constraint]
+            name, j = self._scan_name(j, declstartpos)
+            if j < 0:
+                return j
+            c = rawdata[j:j+1]
+            if c == "":
+                return -1
+            if c == "(":
+                # an enumerated type; look for ')'
+                if ")" in rawdata[j:]:
+                    j = string.find(rawdata, ")", j) + 1
+                else:
+                    return -1
+                while rawdata[j:j+1] in string.whitespace:
+                    j = j + 1
+                if not rawdata[j:]:
+                    # end of buffer, incomplete
+                    return -1
+            else:
+                name, j = self._scan_name(j, declstartpos)
+            c = rawdata[j:j+1]
+            if not c:
+                return -1
+            if c in "'\"":
+                m = _declstringlit_match(rawdata, j)
+                if m:
+                    j = m.end()
+                else:
+                    return -1
+                c = rawdata[j:j+1]
+                if not c:
+                    return -1
+            if c == "#":
+                if rawdata[j:] == "#":
+                    # end of buffer
+                    return -1
+                name, j = self._scan_name(j + 1, declstartpos)
+                if j < 0:
+                    return j
+                c = rawdata[j:j+1]
+                if not c:
+                    return -1
+            if c == '>':
+                # all done
+                return j + 1
+
+    # Internal -- scan past <!NOTATION declarations
+    def _parse_doctype_notation(self, i, declstartpos):
+        name, j = self._scan_name(i, declstartpos)
+        if j < 0:
+            return j
+        rawdata = self.rawdata
+        while 1:
+            c = rawdata[j:j+1]
+            if not c:
+                # end of buffer; incomplete
+                return -1
+            if c == '>':
+                return j + 1
+            if c in "'\"":
+                m = _declstringlit_match(rawdata, j)
+                if not m:
+                    return -1
+                j = m.end()
+            else:
+                name, j = self._scan_name(j, declstartpos)
+                if j < 0:
+                    return j
+
+    # Internal -- scan past <!ENTITY declarations
+    def _parse_doctype_entity(self, i, declstartpos):
+        rawdata = self.rawdata
+        if rawdata[i:i+1] == "%":
+            j = i + 1
+            while 1:
+                c = rawdata[j:j+1]
+                if not c:
+                    return -1
+                if c in string.whitespace:
+                    j = j + 1
+                else:
+                    break
+        else:
+            j = i
+        name, j = self._scan_name(j, declstartpos)
+        if j < 0:
+            return j
+        while 1:
+            c = self.rawdata[j:j+1]
+            if not c:
+                return -1
+            if c in "'\"":
+                m = _declstringlit_match(rawdata, j)
+                if m:
+                    j = m.end()
+                else:
+                    return -1    # incomplete
+            elif c == ">":
+                return j + 1
+            else:
+                name, j = self._scan_name(j, declstartpos)
+                if j < 0:
+                    return j
+
+    # Internal -- scan a name token and the new position and the token, or
+    # return -1 if we've reached the end of the buffer.
+    def _scan_name(self, i, declstartpos):
+        rawdata = self.rawdata
+        n = len(rawdata)
+        if i == n:
+            return None, -1
+        m = _declname_match(rawdata, i)
+        if m:
+            s = m.group()
+            name = s.strip()
+            if (i + len(s)) == n:
+                return None, -1  # end of buffer
+            return string.lower(name), m.end()
+        else:
+            self.updatepos(declstartpos, i)
+            self.error("expected name token")
+
+    # To be overridden -- handlers for unknown objects
+    def unknown_decl(self, data):
+        pass