[Pywikipedia-l] SVN: [3920] trunk/pywikiparser/Parser.py - pywikibot

29 Jul 2007

Revision: 3920
Author:   valhallasw
Date:     2007-07-29 20:14:00 +0000 (Sun, 29 Jul 2007)
Log Message:
-----------
Added new Parser.py
Added Paths:
-----------
    trunk/pywikiparser/Parser.py
Added: trunk/pywikiparser/Parser.py
===================================================================

--- trunk/pywikiparser/Parser.py	                        (rev 0)
+++ trunk/pywikiparser/Parser.py	2007-07-29 20:14:00 UTC (rev 3920)
@@ -0,0 +1,170 @@
+# -*- coding: utf-8  -*-
+""" Mediawiki wikitext parser """
+#
+# (C) 2007 Merlijn 'valhallasw' van Deen
+#
+# Distributed under the terms of the MIT license.
+#
+__version__ = '$Id$'
+
+import warnings
+
+import ObjectTree as dom
+from BufferedReader import BufferedReader
+
+from Lexer import Lexer, Tokens
+
+class ParseError(Exception):
+    """ Parsing Error """
+
+class Parser:
+    def __init__(self, data):
+        self.lex = BufferedReader(Lexer(data).lexer())
+        
+    def expect(self, tokens):
+        if not isinstance(tokens, list):
+            tokens = [tokens,]
+           
+        data = self.lex.peek()
+        if data[0] in tokens:
+            return self.lex.next()
+        else:
+            raise ParseError('%r is not one of %r' % (data[0], tokens))
+
+    def parse(self, breaktoken=[]):
+        self.root = dom.Element('wikipage')
+        self.par = self.root.appendElement('p')
+        self.italic = False
+        self.bold = False
+        try:
+            while(True):
+                token = self.lex.peek()
+                if token[0] in breaktoken:
+                    break
+
+                node = self.parsetoken(token)
+                print "Adding %r (was %r)" % (node,token)
+                self.par.extend(node)
+                self.lex.commit()
+                
+        except StopIteration: pass
+        return self.root
+        
+    def parsetoken(self, token):
+        # The function to call is parser<token>
+        exec("data = self.parse%s()" % token[0].name, globals(), locals())
+        return data
+        
+    def parseEOF(self):
+        token = self.expect(Tokens.EOF)
+        raise StopIteration
+        
+    def parseNEWPAR(self):
+        token = self.expect(Tokens.NEWPAR)
+        self.par = self.root.appendElement('p')
+        self.bold = False
+        self.italic = False
+        return []
+                
+    def parseAPOSTROPHE(self):
+        token = self.expect(Tokens.APOSTROPHE)
+        retval = []
+        
+        #prepare length
+        if (token[1] == 1):
+            retval.append(''')
+        elif (token[1] == 4):
+            retval.append(''')
+            token[1] = 3
+        elif (token[1] > 5):
+            retval.append(''' * (token[1]-5))
+            token[1] = 5
+        
+        # determine changes
+        newitalic = self.italic
+        newbold  = self.bold
+        
+        if token[1] == 2: #toggle italic
+            newitalic = not self.italic
+        elif token[1] == 3: #toggle bold
+            newbold  = not self.bold
+        elif token[1] == 5: #toggle both
+            newitalic = not self.italic
+            newbold = not self.bold
+        
+        print 'bold: %r>%r italic: %r>%r' % (self.bold, newbold, self.italic, newitalic)
+        if self.italic and not newitalic:
+            if self.par.name == 'i' or not newbold:
+                self.par = self.par.parent
+            else:
+                self.par = self.par.parent.parent.appendElement('b')
+            self.italic = False
+        if self.bold and not newbold:
+            if self.par.name == 'b' or not newitalic:
+                self.par = self.par.parent
+            else:
+                self.par = self.par.parent.parent.appendElement('i')
+            self.bold = False
+        if not self.italic and newitalic:
+            self.par = self.par.appendElement('i')
+            self.italic = True
+        if not self.bold and newbold:
+            self.par = self.par.appendElement('b')   
+            self.bold = True
+        return retval     
+    
+    def parseSQRE_CLOSE(self):
+        token = self.expect(Tokens.SQRE_CLOSE)
+        return [']'*token[1]]
+        
+    def parsePIPE(self):
+        token = self.expect(Tokens.PIPE)
+        return ['|'*token[1]]
+        
+    def parseEQUAL_SIGN(self):
+        token = self.expect(Tokens.EQUAL_SIGN)
+        return ['='*token[1]]
+        
+    def parseCURL_CLOSE(self):
+        token = self.expect(Tokens.CURL_CLOSE)
+        return ['}'*token[1]]
+
+    def parseANGL_CLOSE(self):
+        token = self.expect(Tokens.ANGL_CLOSE)
+        return ['>'*token[1]]
+
+    def parseTAB_NEWLINE(self):
+        token = self.expect(Tokens.TAB_NEWLINE)
+        return ['|-']
+
+    def parseTAB_CLOSE(self):
+        token = self.expect(Tokens.TAB_CLOSE)
+        return ['|}']
+
+    def parseWHITESPACE(self):
+        return self.parseTEXT()
+
+    def parseTEXT(self):
+        text = ''
+        try:
+            while(True):
+                text += self.expect([Tokens.TEXT, Tokens.WHITESPACE])[1]
+        except ParseError: pass
+        if text:
+            return [text]
+        else:
+            return []
+
+    def parseSQRE_OPEN(self):
+        token = self.expect(Tokens.SQRE_OPEN)
+    def parseCURL_OPEN(self):
+        token = self.expect(Tokens.CURL_OPEN)
+    def parseANGL_OPEN(self):
+        token = self.expect(Tokens.ANGL_OPEN)
+    def parseTAB_OPEN(self):
+        token = self.expect(Tokens.TAB_OPEN)
+
+
+
+        
+             
\ No newline at end of file
Property changes on: trunk/pywikiparser/Parser.py
___________________________________________________________________
Name: svn:keywords
   + Id *.c = svn:eol-style=native *.cpp = svn:eol-style=native *.h = svn:eol-style=native *.dsp = svn:eol-style=CRLF *.dsw = svn:eol-style=CRLF *.sh = svn:eol-style=native
Name: svn:executable *.txt
   + svn:eol-style=native *.png = svn:mime-type=image/png *.jpg = svn:mime-type=image/jpeg Makefile = svn:eol-style=native
Name: svn:eol-style
   + native

    