From 5fde0330375982b238adf92abcd577707e0a0049 Mon Sep 17 00:00:00 2001 From: Mantavya Gajjar Date: Fri, 21 Nov 2008 18:00:50 +0530 Subject: [PATCH] improve the module : wiki bzr revid: mga@tinyerp.com-20081121123050-2hq03amrvi7a1kvg --- addons/wiki/Cell.py | 18 - addons/wiki/Html2Wiki.py | 290 ---------------- addons/wiki/IndexClient.py | 12 - addons/wiki/IndexServer.py | 178 ---------- addons/wiki/Plex/._.DS_Store | Bin 82 -> 0 bytes addons/wiki/Plex/._Actions.py | Bin 82 -> 0 bytes addons/wiki/Plex/._DFA.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Errors.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Lexicons.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Machines.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Regexps.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Scanners.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Timing.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Traditional.py | Bin 82 -> 0 bytes addons/wiki/Plex/._Transitions.py | Bin 82 -> 0 bytes addons/wiki/Plex/.___init__.py | Bin 82 -> 0 bytes addons/wiki/Plex/._test_tm.py | Bin 82 -> 0 bytes addons/wiki/Plex/Actions.py | 109 ------ addons/wiki/Plex/DFA.py | 156 --------- addons/wiki/Plex/Errors.py | 52 --- addons/wiki/Plex/Lexicons.py | 192 ---------- addons/wiki/Plex/Machines.py | 326 ----------------- addons/wiki/Plex/Regexps.py | 557 ------------------------------ addons/wiki/Plex/Scanners.py | 377 -------------------- addons/wiki/Plex/Timing.py | 22 -- addons/wiki/Plex/Traditional.py | 154 --------- addons/wiki/Plex/Transitions.py | 252 -------------- addons/wiki/Plex/__init__.py | 40 --- addons/wiki/Plex/test_tm.py | 24 -- addons/wiki/Wiki2Html.py | 332 ------------------ addons/wiki/WikiParser.py | 417 ---------------------- addons/wiki/__init__.py | 8 - addons/wiki/__terp__.py | 11 +- addons/wiki/config.py | 7 - addons/wiki/wiki.py | 187 ++-------- addons/wiki/wiki_data.xml | 117 ++++++- addons/wiki/wiki_view.xml | 165 ++------- 37 files changed, 182 insertions(+), 3821 deletions(-) delete mode 100755 addons/wiki/Cell.py delete mode 100755 addons/wiki/Html2Wiki.py delete mode 100755 addons/wiki/IndexClient.py delete mode 100755 addons/wiki/IndexServer.py delete mode 100755 addons/wiki/Plex/._.DS_Store delete mode 100755 addons/wiki/Plex/._Actions.py delete mode 100755 addons/wiki/Plex/._DFA.py delete mode 100755 addons/wiki/Plex/._Errors.py delete mode 100755 addons/wiki/Plex/._Lexicons.py delete mode 100755 addons/wiki/Plex/._Machines.py delete mode 100755 addons/wiki/Plex/._Regexps.py delete mode 100755 addons/wiki/Plex/._Scanners.py delete mode 100755 addons/wiki/Plex/._Timing.py delete mode 100755 addons/wiki/Plex/._Traditional.py delete mode 100755 addons/wiki/Plex/._Transitions.py delete mode 100755 addons/wiki/Plex/.___init__.py delete mode 100755 addons/wiki/Plex/._test_tm.py delete mode 100755 addons/wiki/Plex/Actions.py delete mode 100755 addons/wiki/Plex/DFA.py delete mode 100755 addons/wiki/Plex/Errors.py delete mode 100755 addons/wiki/Plex/Lexicons.py delete mode 100755 addons/wiki/Plex/Machines.py delete mode 100755 addons/wiki/Plex/Regexps.py delete mode 100755 addons/wiki/Plex/Scanners.py delete mode 100755 addons/wiki/Plex/Timing.py delete mode 100755 addons/wiki/Plex/Traditional.py delete mode 100755 addons/wiki/Plex/Transitions.py delete mode 100755 addons/wiki/Plex/__init__.py delete mode 100755 addons/wiki/Plex/test_tm.py delete mode 100755 addons/wiki/Wiki2Html.py delete mode 100755 addons/wiki/WikiParser.py mode change 100755 => 100644 addons/wiki/__init__.py delete mode 100755 addons/wiki/config.py diff --git a/addons/wiki/Cell.py b/addons/wiki/Cell.py deleted file mode 100755 index de2c606eb8c..00000000000 --- a/addons/wiki/Cell.py +++ /dev/null @@ -1,18 +0,0 @@ -# Copyright (C) 2006 Samuel Abels, http://debain.org -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2, as -# published by the Free Software Foundation. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -class Cell: - data = '' - colspan = 1 - rowspan = 1 diff --git a/addons/wiki/Html2Wiki.py b/addons/wiki/Html2Wiki.py deleted file mode 100755 index e16ad08fd19..00000000000 --- a/addons/wiki/Html2Wiki.py +++ /dev/null @@ -1,290 +0,0 @@ -# Copyright (C) 2006 Samuel Abels, http://debain.org -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2, as -# published by the Free Software Foundation. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -import HTMLParser, re, sys -from Cell import Cell - -class Html2Wiki(HTMLParser.HTMLParser): - def __init__(self): - HTMLParser.HTMLParser.__init__(self) - self.wiki = '' - self.buffer = '' - self.indent = 0 - self.linebreak = '\n' - self.rows = [] - self.cells = [] - self.in_table = False - self.in_td = False - self.in_heading = False - self.in_ul = False - self.in_ol = False - self.in_li = False - self.in_a = False - self.in_pre = False - self.last_href = '' - - def __output(self, text, linebreak = True): - self.buffer += (' ' * self.indent * 2) - self.buffer += text + self.linebreak - - def __flush(self): - self.wiki += self.buffer - self.buffer = '' - - def handle_starttag(self, tag, attrs): - if tag == 'table': self.start_table() - elif tag == 'tr': self.start_tr() - elif tag == 'th': self.start_th(attrs) - elif tag == 'td': self.start_td(attrs) - elif tag == 'h1': self.start_h1() - elif tag == 'h2': self.start_h2() - elif tag == 'h3': self.start_h3() - elif tag == 'ul': self.start_ul() - elif tag == 'ol': self.start_ol() - elif tag == 'li': self.start_li() - elif tag == 'i': self.start_i() - elif tag == 'b': self.start_b() - elif tag == 'u': self.start_u() - elif tag == 'a': self.start_a(attrs) - elif tag == 'pre': self.start_pre() - elif tag == 'strike': self.start_strike() - elif tag == 'br': self.newline() - - def handle_endtag(self, tag): - if tag == 'table': self.end_table(); - elif tag == 'tr': self.end_tr() - elif tag == 'th': self.end_th() - elif tag == 'td': self.end_td() - elif tag == 'h1': self.end_h1() - elif tag == 'h2': self.end_h2() - elif tag == 'h3': self.end_h3() - elif tag == 'ul': self.end_ul() - elif tag == 'ol': self.end_ol() - elif tag == 'li': self.end_li() - elif tag == 'i': self.end_i() - elif tag == 'b': self.end_b() - elif tag == 'u': self.end_u() - elif tag == 'a': self.end_a() - elif tag == 'pre': self.end_pre() - elif tag == 'strike': self.end_strike() - - def start_h1(self): - self.buffer += '=' - - def end_h1(self): - self.buffer += '=\n\n' - - def start_h2(self): - self.buffer += '==' - - def end_h2(self): - self.buffer += '==\n\n' - - def start_h3(self): - self.buffer += '===' - - def end_h3(self): - self.buffer += '===\n\n' - - def start_ul(self): - self.in_ul = True - - def end_ul(self): - self.in_ul = False - - def start_ol(self): - self.in_ol = True - - def end_ol(self): - self.in_ol = False - - def start_li(self): - self.in_li = True - if self.in_ol: - self.buffer += '# ' - elif self.in_ul: - self.buffer += '* ' - - def end_li(self): - self.in_li = False - - def start_i(self): - self.buffer += '/' - - def end_i(self): - self.buffer += '/' - - def start_b(self): - self.buffer += '*' - - def end_b(self): - self.buffer += '*' - - def start_u(self): - self.buffer += '_' - - def end_u(self): - self.buffer += '_' - - def start_a(self, attrs): - self.in_a = True - self.last_href = '' - for key, value in attrs: - if key == 'href': - self.last_href = value - self.buffer += '[' + self.last_href - - def end_a(self): - self.in_a = False - self.buffer += ']' - - def start_pre(self): - self.in_pre = True - self.buffer += '#Text\n' - - def end_pre(self): - self.in_pre = False - self.buffer += '#End\n' - - def start_strike(self): - self.buffer += '-' - - def end_strike(self): - self.buffer += '-' - - def start_table(self): - self.in_table = True - - def start_tr(self): - pass - - def start_th(self, attrs): - self.in_heading = True - self.start_td(attrs) - - def start_td(self, attrs): - self.__flush() - self.in_td = True - cell = Cell() - for key, value in attrs: - if key == 'rowspan': - cell.rowspan = int(value) - elif key == 'colspan': - cell.colspan = int(value) - self.cells.append(cell) - - def handle_data(self, data): - if not self.in_pre: - data = data.replace('\n', '') - if self.in_a: - if data == self.last_href: - return - self.buffer += ' ' - if self.in_li: - self.buffer += data.strip() + '\n' - if self.in_ul or self.in_ol: - self.__flush() - elif self.in_td: - self.buffer += data - elif not self.in_table: - self.buffer += data - self.__flush() - - def end_td(self): - self.cells[-1].data += self.buffer.strip() - self.buffer = '' - self.in_td = False - - def end_th(self): - self.end_td() - - def end_tr(self): - if len(self.cells) is 0: - return - if self.in_heading: - self.__output('#Heading') - self.in_heading = False - else: - self.__output('#Row') - self.indent += 1 - line = ('|' * self.cells[0].colspan) + ' ' + self.cells[0].data.strip() - for cell in self.cells[1:]: - line += ' ' + ('|' * cell.colspan) + ' ' + cell.data.strip() - if len(line) <= 80: - self.__output(line) - else: - for cell in self.cells: - self.__output(('|' * cell.colspan) + ' ' + cell.data.strip()) - self.cells = [] - self.indent -= 1 - self.__flush() - - def end_table(self): - self.in_table = False - self.__flush() - - def newline(self): - self.buffer += '\n' - - -if __name__ == '__main__': - import unittest - import os - from Wiki2Html import Wiki2Html - - class Wiki2HtmlTest(unittest.TestCase): - def runTest(self): - # Read the entire file into one string. - filename = 'markup.txt' - infile = open(filename, 'r') - in_str = infile.read() - infile.close() - - # Convert Wiki to HTML. - parser = Wiki2Html() - parser.read(filename) - html1 = parser.html - #print html1 - - # Convert the HTML back to Wiki. - parser = Html2Wiki() - parser.feed(html1) - wiki = parser.wiki - #print wiki - - # Write the wiki to a file. - # The result contains an extra newline to mark a table end. - # This is generally ok, but would break the unit test, so we - # remove the last character before writing. - fd = open(filename + '.tmp', 'w') - fd.write(wiki[:-1]) - fd.close() - - # Convert the new Wiki file to HTML again. - parser = Wiki2Html() - parser.read(filename + '.tmp') - html2 = parser.html - #print html2 - - # Clean up. - os.remove(filename + '.tmp') - - # Make sure that the model is complete. - assert len(in_str) > 10 - assert len(html1) > 10 - assert html1 == html2 - - testcase = Wiki2HtmlTest() - runner = unittest.TextTestRunner() - runner.run(testcase) diff --git a/addons/wiki/IndexClient.py b/addons/wiki/IndexClient.py deleted file mode 100755 index 1bf036f9e20..00000000000 --- a/addons/wiki/IndexClient.py +++ /dev/null @@ -1,12 +0,0 @@ -#!/usr/bin/python - -import xmlrpclib - -tiny_host = 'localhost' -tiny_port = 8000 - -url = 'http://%s:%s' % (tiny_host, tiny_port) -proxy = xmlrpclib.ServerProxy(url); - -proxy.init('terp', 3, 'admin') -print proxy.search('china') \ No newline at end of file diff --git a/addons/wiki/IndexServer.py b/addons/wiki/IndexServer.py deleted file mode 100755 index 60adcd17bba..00000000000 --- a/addons/wiki/IndexServer.py +++ /dev/null @@ -1,178 +0,0 @@ -#!/usr/bin/python - -from SimpleXMLRPCServer import SimpleXMLRPCServer -import os -import csv -from config import * -import xmlrpclib -import PyLucene -import threading - -class IndexServer(threading.Thread): - - def __init__(self): - super(IndexServer,self).__init__() - self.path = os.path.join('/tmp', 'index') - - def initIndex(self, database, user, password, new=False): - self.database = database - self.user = user - self.password = password - self.new = new - self.writer = None - - def open(self): - if not os.path.exists(self.path): - os.mkdir(path) - self.new = True - - store = PyLucene.FSDirectory.getDirectory(path, self.new) - self.writer = PyLucene.IndexWriter(store, PyLucene.StandardAnalyzer(), self.new) - url = 'http://%s:%s/xmlrpc/object' % (tiny_host, str(tiny_port)) - self.proxy = xmlrpclib.ServerProxy(url); - return True - - def addDocument(self, model, id, data): - - doc = PyLucene.Document() - doc.add(PyLucene.Field("model", model, - PyLucene.Field.Store.YES, - PyLucene.Field.Index.UN_TOKENIZED)) - indexid=str(id) - - doc.add(PyLucene.Field("id", indexid, - PyLucene.Field.Store.YES, - PyLucene.Field.Index.UN_TOKENIZED)) - - doc.add(PyLucene.Field("contents", data, - PyLucene.Field.Store.YES, - PyLucene.Field.Index.TOKENIZED)) - self.writer.addDocument(doc) - - return True - - def doIndex(self, models=None): - - self.open() - - toIndex = [] - if models is None: - toIndex = self.proxy.execute(self.database, self.user, self.password, 'ir.model' ,'search', []) - else: - toIndex = models - - models = self.proxy.execute(self.database, self.user, self.password, 'ir.model' ,'read', toIndex, ['model']) - for mod in models: - res_ids = self.proxy.execute(self.database, self.user, self.password, mod['model'], 'search', []) - - if str(mod['model']).startswith('ir'): - continue - - if str(mod['model']).startswith('res.currency'): - continue - - print 'creating index for : ', str(mod['model']) - try: - res_datas = self.proxy.execute(self.database, self.user, self.password, mod['model'], 'read', res_ids) - except Exception, e: - print e - continue - - for res_data in res_datas: - self.addDocument(mod['model'], res_data['id'], ' '.join(map(str,res_data.values()))) - - self.new = False - self.close() - return True - - def reIndex(self, models = None): - self.new = True - self.doIndex(models) - - def close(self): - self.writer.close() - return True - - def addRecord(self, model, id, data): - self.new = False - self.open() - doc = PyLucene.Document() - doc.add(PyLucene.Field("model", model, - PyLucene.Field.Store.YES, - PyLucene.Field.Index.UN_TOKENIZED)) - indexid=str(id) - - doc.add(PyLucene.Field("id", indexid, - PyLucene.Field.Store.YES, - PyLucene.Field.Index.UN_TOKENIZED)) - - doc.add(PyLucene.Field("contents", data, - PyLucene.Field.Store.YES, - PyLucene.Field.Index.TOKENIZED)) - self.writer.addDocument(doc) - self.close() - return True - - def search(self, keys): - directory = PyLucene.FSDirectory.getDirectory(self.path, False) - searcher = PyLucene.IndexSearcher(directory) - analyzer = PyLucene.StandardAnalyzer() - - query = PyLucene.QueryParser("contents", analyzer).parse(keys) - hits = searcher.search(query) - count= hits.length() - result = {} - - for i, doc in hits: - model = doc.get('model') - id = doc.get('id') - - if result.has_key(model): - ids = result.get(model) - ids.append(id) - else: - ids = [] - ids.append(id) - result[model] = ids - - searcher.close() - - if result.__len__() <=0 : - result = False - - return result - - def run(self): - server = SimpleXMLRPCServer((index_server,index_port),allow_none=True) - indexer = IndexServer() - server.register_instance(indexer, True) - server.register_function(indexer.initIndex, 'init') - server.register_function(indexer.open, 'open') - server.register_function(indexer.addRecord, 'add') - server.register_function(indexer.doIndex, 'index') - server.register_function(indexer.reIndex, 'reindex') - server.register_function(indexer.close, 'close') - server.register_function(indexer.search, 'search') - server.register_introspection_functions() - server.serve_forever() -#end class - -server = SimpleXMLRPCServer((index_server,index_port),allow_none=True) -indexer = IndexServer() -server.register_function(indexer.initIndex, 'init') -server.register_function(indexer.open, 'open') -server.register_function(indexer.addRecord, 'add') -server.register_function(indexer.doIndex, 'index') -server.register_function(indexer.reIndex, 'reindex') -server.register_function(indexer.close, 'close') -server.register_function(indexer.search, 'search') -server.register_introspection_functions() -server.register_multicall_functions() -server.serve_forever() -# -#try: -# print 'Starting Index Server', index_server, index_port -# server = IndexServer() -# server.start() -#except Exception , e: -# print e diff --git a/addons/wiki/Plex/._.DS_Store b/addons/wiki/Plex/._.DS_Store deleted file mode 100755 index 460d887a2e21de5e7ccf222b0fdc4fbe43f67e75..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 ucmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4Dn2M%x+Dgyuy>I7i` diff --git a/addons/wiki/Plex/._Actions.py b/addons/wiki/Plex/._Actions.py deleted file mode 100755 index 1ab1d742745f6bfeb409e4c66870229a2212ce20..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!3g4j2@r#U Kp#e-XFaQ8nU$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!3g3k1Q8I> G0Hpz9KnKqN diff --git a/addons/wiki/Plex/._Errors.py b/addons/wiki/Plex/._Errors.py deleted file mode 100755 index af4b4136e43d865105306f1963cae86c6531f44c..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!3bnCDuP5H IpaDt)09e!qPyhe` diff --git a/addons/wiki/Plex/._Lexicons.py b/addons/wiki/Plex/._Lexicons.py deleted file mode 100755 index e133ecc39a18d80b06f169b8e0325d401e70de33..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|a1#*hdS Jfq(`m4FF;82gLvY diff --git a/addons/wiki/Plex/._Machines.py b/addons/wiki/Plex/._Machines.py deleted file mode 100755 index 9abffbaadfa7439d8d9a9383c72e136a69667227..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|a1#;6Dq Jfq(`m4FFw22ZjIu diff --git a/addons/wiki/Plex/._Regexps.py b/addons/wiki/Plex/._Regexps.py deleted file mode 100755 index 68c7c99266aec747455b370c191ec2cc52119933..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|an!;lCP Jfq(`m4FG0b2m1g3 diff --git a/addons/wiki/Plex/._Scanners.py b/addons/wiki/Plex/._Scanners.py deleted file mode 100755 index 42c3ef2ac8d51330cb47de5a6b07826e6c7efe28..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|an!>9-n Jfq(`m4FF-V2fP3P diff --git a/addons/wiki/Plex/._Timing.py b/addons/wiki/Plex/._Timing.py deleted file mode 100755 index a79e35c322d4c8441fe057a9e1f54f279ee6d5fa..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|a{h~Xee J1OghMGyrkx2$28) diff --git a/addons/wiki/Plex/._Traditional.py b/addons/wiki/Plex/._Traditional.py deleted file mode 100755 index 39ffda334b8a0d0e5a25c24aadc6015f3f20fe65..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|aHg8@ju IKm(Kk0B9Hp2LJ#7 diff --git a/addons/wiki/Plex/._Transitions.py b/addons/wiki/Plex/._Transitions.py deleted file mode 100755 index a1afe03ef1d970299ca2136ad24e55da30954572..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|aHgW(`Z J1OghMGyry32*&^b diff --git a/addons/wiki/Plex/.___init__.py b/addons/wiki/Plex/.___init__.py deleted file mode 100755 index 88f160bc02ea3ce7c642694662efefa90c389932..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|bK$G`{@ Jfq(`m4FFf12R;A* diff --git a/addons/wiki/Plex/._test_tm.py b/addons/wiki/Plex/._test_tm.py deleted file mode 100755 index a5fdaefe5e8de19103ca5a112573d9007c4f3574..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 82 zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDI}u>uf-_(4F-5aJpU5~P)!!N|a{h#?Uq J0s#$B8USj_2r&Qv diff --git a/addons/wiki/Plex/Actions.py b/addons/wiki/Plex/Actions.py deleted file mode 100755 index 23253a905a1..00000000000 --- a/addons/wiki/Plex/Actions.py +++ /dev/null @@ -1,109 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Actions for use in token specifications -# -#======================================================================= - -class Action: - - def same_as(self, other): - return self is other - - -class Return(Action): - """ - Internal Plex action which causes |value| to - be returned as the value of the associated token - """ - - value = None - - def __init__(self, value): - self.value = value - - def perform(self, token_stream, text): - return self.value - - def same_as(self, other): - return isinstance(other, Return) and self.value == other.value - - def __repr__(self): - return "Return(%s)" % repr(self.value) - - -class Call(Action): - """ - Internal Plex action which causes a function to be called. - """ - - function = None - - def __init__(self, function): - self.function = function - - def perform(self, token_stream, text): - return self.function(token_stream, text) - - def __repr__(self): - return "Call(%s)" % self.function.__name__ - - def same_as(self, other): - return isinstance(other, Call) and self.function is other.function - - -class Begin(Action): - """ - Begin(state_name) is a Plex action which causes the Scanner to - enter the state |state_name|. See the docstring of Plex.Lexicon - for more information. - """ - - state_name = None - - def __init__(self, state_name): - self.state_name = state_name - - def perform(self, token_stream, text): - token_stream.begin(self.state_name) - - def __repr__(self): - return "Begin(%s)" % self.state_name - - def same_as(self, other): - return isinstance(other, Begin) and self.state_name == other.state_name - - -class Ignore(Action): - """ - IGNORE is a Plex action which causes its associated token - to be ignored. See the docstring of Plex.Lexicon for more - information. - """ - def perform(self, token_stream, text): - return None - - def __repr__(self): - return "IGNORE" - -IGNORE = Ignore() -IGNORE.__doc__ = Ignore.__doc__ - -class Text(Action): - """ - TEXT is a Plex action which causes the text of a token to - be returned as the value of the token. See the docstring of - Plex.Lexicon for more information. - """ - - def perform(self, token_stream, text): - return text - - def __repr__(self): - return "TEXT" - -TEXT = Text() -TEXT.__doc__ = Text.__doc__ - - diff --git a/addons/wiki/Plex/DFA.py b/addons/wiki/Plex/DFA.py deleted file mode 100755 index 2c0004b092e..00000000000 --- a/addons/wiki/Plex/DFA.py +++ /dev/null @@ -1,156 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Converting NFA to DFA -# -#======================================================================= - -import Machines -from Machines import LOWEST_PRIORITY -from Transitions import TransitionMap - -def nfa_to_dfa(old_machine, debug = None): - """ - Given a nondeterministic Machine, return a new equivalent - Machine which is deterministic. - """ - # We build a new machine whose states correspond to sets of states - # in the old machine. Initially we add a new state corresponding to - # the epsilon-closure of each initial old state. Then we give transitions - # to each new state which are the union of all transitions out of any - # of the corresponding old states. The new state reached on a given - # character is the one corresponding to the set of states reachable - # on that character from any of the old states. As new combinations of - # old states are created, new states are added as needed until closure - # is reached. - new_machine = Machines.FastMachine() - state_map = StateMap(new_machine) - # Seed the process using the initial states of the old machine. - # Make the corresponding new states into initial states of the new - # machine with the same names. - for (key, old_state) in old_machine.initial_states.items(): - new_state = state_map.old_to_new(epsilon_closure(old_state)) - new_machine.make_initial_state(key, new_state) - # Tricky bit here: we add things to the end of this list while we're - # iterating over it. The iteration stops when closure is achieved. - for new_state in new_machine.states: - transitions = TransitionMap() - for old_state in state_map.new_to_old(new_state).keys(): - for event, old_target_states in old_state.transitions.items(): - if event and old_target_states: - transitions.add_set(event, set_epsilon_closure(old_target_states)) - for event, old_states in transitions.items(): - new_machine.add_transitions(new_state, event, state_map.old_to_new(old_states)) - if debug: - debug.write("\n===== State Mapping =====\n") - state_map.dump(debug) - return new_machine - -def set_epsilon_closure(state_set): - """ - Given a set of states, return the union of the epsilon - closures of its member states. - """ - result = {} - for state1 in state_set.keys(): - for state2 in epsilon_closure(state1).keys(): - result[state2] = 1 - return result - -def epsilon_closure(state): - """ - Return the set of states reachable from the given state - by epsilon moves. - """ - # Cache the result - result = state.epsilon_closure - if result is None: - result = {} - state.epsilon_closure = result - add_to_epsilon_closure(result, state) - return result - -def add_to_epsilon_closure(state_set, state): - """ - Recursively add to |state_set| states reachable from the given state - by epsilon moves. - """ - if not state_set.get(state, 0): - state_set[state] = 1 - state_set_2 = state.transitions.get_epsilon() - if state_set_2: - for state2 in state_set_2.keys(): - add_to_epsilon_closure(state_set, state2) - -class StateMap: - """ - Helper class used by nfa_to_dfa() to map back and forth between - sets of states from the old machine and states of the new machine. - """ - new_machine = None # Machine - old_to_new_dict = None # {(old_state,...) : new_state} - new_to_old_dict = None # {id(new_state) : old_state_set} - - def __init__(self, new_machine): - self.new_machine = new_machine - self.old_to_new_dict = {} - self.new_to_old_dict= {} - - def old_to_new(self, old_state_set): - """ - Return the state of the new machine corresponding to the - set of old machine states represented by |state_set|. A new - state will be created if necessary. If any of the old states - are accepting states, the new state will be an accepting state - with the highest priority action from the old states. - """ - key = self.make_key(old_state_set) - new_state = self.old_to_new_dict.get(key, None) - if not new_state: - action = self.highest_priority_action(old_state_set) - new_state = self.new_machine.new_state(action) - self.old_to_new_dict[key] = new_state - self.new_to_old_dict[id(new_state)] = old_state_set - #for old_state in old_state_set.keys(): - #new_state.merge_actions(old_state) - return new_state - - def highest_priority_action(self, state_set): - best_action = None - best_priority = LOWEST_PRIORITY - for state in state_set.keys(): - priority = state.action_priority - if priority > best_priority: - best_action = state.action - best_priority = priority - return best_action - -# def old_to_new_set(self, old_state_set): -# """ -# Return the new state corresponding to a set of old states as -# a singleton set. -# """ -# return {self.old_to_new(old_state_set):1} - - def new_to_old(self, new_state): - """Given a new state, return a set of corresponding old states.""" - return self.new_to_old_dict[id(new_state)] - - def make_key(self, state_set): - """ - Convert a set of states into a uniquified - sorted tuple suitable for use as a dictionary key. - """ - lst = state_set.keys() - lst.sort() - return tuple(lst) - - def dump(self, file): - from Transitions import state_set_str - for new_state in self.new_machine.states: - old_state_set = self.new_to_old_dict[id(new_state)] - file.write(" State %s <-- %s\n" % ( - new_state['number'], state_set_str(old_state_set))) - - diff --git a/addons/wiki/Plex/Errors.py b/addons/wiki/Plex/Errors.py deleted file mode 100755 index ae033672b50..00000000000 --- a/addons/wiki/Plex/Errors.py +++ /dev/null @@ -1,52 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Exception classes -# -#======================================================================= - -import exceptions - -class PlexError(exceptions.Exception): - message = "" - -class PlexTypeError(PlexError, TypeError): - pass - -class PlexValueError(PlexError, ValueError): - pass - -class InvalidRegex(PlexError): - pass - -class InvalidToken(PlexError): - - def __init__(self, token_number, message): - PlexError.__init__(self, "Token number %d: %s" % (token_number, message)) - -class InvalidScanner(PlexError): - pass - -class AmbiguousAction(PlexError): - message = "Two tokens with different actions can match the same string" - - def __init__(self): - pass - -class UnrecognizedInput(PlexError): - scanner = None - position = None - state_name = None - - def __init__(self, scanner, state_name): - self.scanner = scanner - self.position = scanner.position() - self.state_name = state_name - - def __str__(self): - return ("'%s', line %d, char %d: Token not recognised in state %s" - % (self.position + (repr(self.state_name),))) - - - diff --git a/addons/wiki/Plex/Lexicons.py b/addons/wiki/Plex/Lexicons.py deleted file mode 100755 index 32b12c431c3..00000000000 --- a/addons/wiki/Plex/Lexicons.py +++ /dev/null @@ -1,192 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Lexical Analyser Specification -# -#======================================================================= - -import types - -import Actions -import DFA -import Errors -import Machines -import Regexps - -# debug_flags for Lexicon constructor -DUMP_NFA = 1 -DUMP_DFA = 2 - -class State: - """ - This class is used as part of a Plex.Lexicon specification to - introduce a user-defined state. - - Constructor: - - State(name, token_specifications) - """ - - name = None - tokens = None - - def __init__(self, name, tokens): - self.name = name - self.tokens = tokens - -class Lexicon: - """ - Lexicon(specification) builds a lexical analyser from the given - |specification|. The specification consists of a list of - specification items. Each specification item may be either: - - 1) A token definition, which is a tuple: - - (pattern, action) - - The |pattern| is a regular axpression built using the - constructors defined in the Plex module. - - The |action| is the action to be performed when this pattern - is recognised (see below). - - 2) A state definition: - - State(name, tokens) - - where |name| is a character string naming the state, - and |tokens| is a list of token definitions as - above. The meaning and usage of states is described - below. - - Actions - ------- - - The |action| in a token specication may be one of three things: - - 1) A function, which is called as follows: - - function(scanner, text) - - where |scanner| is the relevant Scanner instance, and |text| - is the matched text. If the function returns anything - other than None, that value is returned as the value of the - token. If it returns None, scanning continues as if the IGNORE - action were specified (see below). - - 2) One of the following special actions: - - IGNORE means that the recognised characters will be treated as - white space and ignored. Scanning will continue until - the next non-ignored token is recognised before returning. - - TEXT causes the scanned text itself to be returned as the - value of the token. - - 3) Any other value, which is returned as the value of the token. - - States - ------ - - At any given time, the scanner is in one of a number of states. - Associated with each state is a set of possible tokens. When scanning, - only tokens associated with the current state are recognised. - - There is a default state, whose name is the empty string. Token - definitions which are not inside any State definition belong to - the default state. - - The initial state of the scanner is the default state. The state can - be changed in one of two ways: - - 1) Using Begin(state_name) as the action of a token. - - 2) Calling the begin(state_name) method of the Scanner. - - To change back to the default state, use '' as the state name. - """ - - machine = None # Machine - tables = None # StateTableMachine - - def __init__(self, specifications, debug = None, debug_flags = 7, timings = None): - if type(specifications) <> types.ListType: - raise Errors.InvalidScanner("Scanner definition is not a list") - if timings: - from Timing import time - total_time = 0.0 - time1 = time() - nfa = Machines.Machine() - default_initial_state = nfa.new_initial_state('') - token_number = 1 - for spec in specifications: - if isinstance(spec, State): - user_initial_state = nfa.new_initial_state(spec.name) - for token in spec.tokens: - self.add_token_to_machine( - nfa, user_initial_state, token, token_number) - token_number = token_number + 1 - elif type(spec) == types.TupleType: - self.add_token_to_machine( - nfa, default_initial_state, spec, token_number) - token_number = token_number + 1 - else: - raise Errors.InvalidToken( - token_number, - "Expected a token definition (tuple) or State instance") - if timings: - time2 = time() - total_time = total_time + (time2 - time1) - time3 = time() - if debug and (debug_flags & 1): - debug.write("\n============= NFA ===========\n") - nfa.dump(debug) - dfa = DFA.nfa_to_dfa(nfa, debug = (debug_flags & 3) == 3 and debug) - if timings: - time4 = time() - total_time = total_time + (time4 - time3) - if debug and (debug_flags & 2): - debug.write("\n============= DFA ===========\n") - dfa.dump(debug) - if timings: - timings.write("Constructing NFA : %5.2f\n" % (time2 - time1)) - timings.write("Converting to DFA: %5.2f\n" % (time4 - time3)) - timings.write("TOTAL : %5.2f\n" % total_time) - self.machine = dfa - - def add_token_to_machine(self, machine, initial_state, token_spec, token_number): - try: - (re, action_spec) = self.parse_token_definition(token_spec) - # Disabled this -- matching empty strings can be useful - #if re.nullable: - # raise Errors.InvalidToken( - # token_number, "Pattern can match 0 input symbols") - if isinstance(action_spec, Actions.Action): - action = action_spec - elif callable(action_spec): - action = Actions.Call(action_spec) - else: - action = Actions.Return(action_spec) - final_state = machine.new_state() - re.build_machine(machine, initial_state, final_state, - match_bol = 1, nocase = 0) - final_state.set_action(action, priority = -token_number) - except Errors.PlexError, e: - raise e.__class__("Token number %d: %s" % (token_number, e)) - - def parse_token_definition(self, token_spec): - if type(token_spec) <> types.TupleType: - raise Errors.InvalidToken("Token definition is not a tuple") - if len(token_spec) <> 2: - raise Errors.InvalidToken("Wrong number of items in token definition") - pattern, action = token_spec - if not isinstance(pattern, Regexps.RE): - raise Errors.InvalidToken("Pattern is not an RE instance") - return (pattern, action) - - def get_initial_state(self, name): - return self.machine.get_initial_state(name) - - - diff --git a/addons/wiki/Plex/Machines.py b/addons/wiki/Plex/Machines.py deleted file mode 100755 index fb9ba717d80..00000000000 --- a/addons/wiki/Plex/Machines.py +++ /dev/null @@ -1,326 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Classes for building NFAs and DFAs -# -#======================================================================= - -import string -import sys -from sys import maxint -from types import TupleType - -from Transitions import TransitionMap - -LOWEST_PRIORITY = -sys.maxint - -class Machine: - """A collection of Nodes representing an NFA or DFA.""" - states = None # [Node] - next_state_number = 1 - initial_states = None # {(name, bol): Node} - - def __init__(self): - self.states = [] - self.initial_states = {} - - def __del__(self): - #print "Destroying", self ### - for state in self.states: - state.destroy() - - def new_state(self): - """Add a new state to the machine and return it.""" - s = Node() - n = self.next_state_number - self.next_state_number = n + 1 - s.number = n - self.states.append(s) - return s - - def new_initial_state(self, name): - state = self.new_state() - self.make_initial_state(name, state) - return state - - def make_initial_state(self, name, state): - self.initial_states[name] = state - - def get_initial_state(self, name): - return self.initial_states[name] - - def dump(self, file): - file.write("Plex.Machine:\n") - if self.initial_states is not None: - file.write(" Initial states:\n") - for (name, state) in self.initial_states.items(): - file.write(" '%s': %d\n" % (name, state.number)) - for s in self.states: - s.dump(file) - -class Node: - """A state of an NFA or DFA.""" - transitions = None # TransitionMap - action = None # Action - action_priority = None # integer - number = 0 # for debug output - epsilon_closure = None # used by nfa_to_dfa() - - def __init__(self): - # Preinitialise the list of empty transitions, because - # the nfa-to-dfa algorithm needs it - #self.transitions = {'':[]} - self.transitions = TransitionMap() - self.action_priority = LOWEST_PRIORITY - - def destroy(self): - #print "Destroying", self ### - self.transitions = None - self.action = None - self.epsilon_closure = None - - def add_transition(self, event, new_state): - self.transitions.add(event, new_state) - - def link_to(self, state): - """Add an epsilon-move from this state to another state.""" - self.add_transition('', state) - - def set_action(self, action, priority): - """Make this an accepting state with the given action. If - there is already an action, choose the action with highest - priority.""" - if priority > self.action_priority: - self.action = action - self.action_priority = priority - - def get_action(self): - return self.action - - def get_action_priority(self): - return self.action_priority - -# def merge_actions(self, other_state): -# """Merge actions of other state into this state according -# to their priorities.""" -# action = other_state.get_action() -# priority = other_state.get_action_priority() -# self.set_action(action, priority) - - def is_accepting(self): - return self.action is not None - - def __str__(self): - return "State %d" % self.number - - def dump(self, file): - import string - # Header - file.write(" State %d:\n" % self.number) - # Transitions -# self.dump_transitions(file) - self.transitions.dump(file) - # Action - action = self.action - priority = self.action_priority - if action is not None: - file.write(" %s [priority %d]\n" % (action, priority)) - - -class FastMachine: - """ - FastMachine is a deterministic machine represented in a way that - allows fast scanning. - """ - initial_states = None # {state_name:state} - states = None # [state] - # where state = {event:state, 'else':state, 'action':Action} - next_number = 1 # for debugging - - new_state_template = { - '':None, 'bol':None, 'eol':None, 'eof':None, 'else':None - } - - def __init__(self, old_machine = None): - self.initial_states = initial_states = {} - self.states = [] - if old_machine: - self.old_to_new = old_to_new = {} - for old_state in old_machine.states: - new_state = self.new_state() - old_to_new[old_state] = new_state - for name, old_state in old_machine.initial_states.items(): - initial_states[name] = old_to_new[old_state] - for old_state in old_machine.states: - new_state = old_to_new[old_state] - for event, old_state_set in old_state.transitions.items(): - if old_state_set: - new_state[event] = old_to_new[old_state_set.keys()[0]] - else: - new_state[event] = None - new_state['action'] = old_state.action - - def __del__(self): - for state in self.states: - state.clear() - - def new_state(self, action = None): - number = self.next_number - self.next_number = number + 1 - result = self.new_state_template.copy() - result['number'] = number - result['action'] = action - self.states.append(result) - return result - - def make_initial_state(self, name, state): - self.initial_states[name] = state - - def add_transitions(self, state, event, new_state): - if type(event) == TupleType: - code0, code1 = event - if code0 == -maxint: - state['else'] = new_state - elif code1 <> maxint: - while code0 < code1: - state[chr(code0)] = new_state - code0 = code0 + 1 - else: - state[event] = new_state - - def get_initial_state(self, name): - return self.initial_states[name] - - def dump(self, file): - file.write("Plex.FastMachine:\n") - file.write(" Initial states:\n") - for name, state in self.initial_states.items(): - file.write(" %s: %s\n" % (repr(name), state['number'])) - for state in self.states: - self.dump_state(state, file) - - def dump_state(self, state, file): - import string - # Header - file.write(" State %d:\n" % state['number']) - # Transitions - self.dump_transitions(state, file) - # Action - action = state['action'] - if action is not None: - file.write(" %s\n" % action) - - def dump_transitions(self, state, file): - chars_leading_to_state = {} - special_to_state = {} - for (c, s) in state.items(): - if len(c) == 1: - chars = chars_leading_to_state.get(id(s), None) - if chars is None: - chars = [] - chars_leading_to_state[id(s)] = chars - chars.append(c) - elif len(c) <= 4: - special_to_state[c] = s - ranges_to_state = {} - for state in self.states: - char_list = chars_leading_to_state.get(id(state), None) - if char_list: - ranges = self.chars_to_ranges(char_list) - ranges_to_state[ranges] = state - ranges_list = ranges_to_state.keys() - ranges_list.sort() - for ranges in ranges_list: - key = self.ranges_to_string(ranges) - state = ranges_to_state[ranges] - file.write(" %s --> State %d\n" % (key, state['number'])) - for key in ('bol', 'eol', 'eof', 'else'): - state = special_to_state.get(key, None) - if state: - file.write(" %s --> State %d\n" % (key, state['number'])) - - def chars_to_ranges(self, char_list): - char_list.sort() - i = 0 - n = len(char_list) - result = [] - while i < n: - c1 = ord(char_list[i]) - c2 = c1 - i = i + 1 - while i < n and ord(char_list[i]) == c2 + 1: - i = i + 1 - c2 = c2 + 1 - result.append((chr(c1), chr(c2))) - return tuple(result) - - def ranges_to_string(self, range_list): - return string.join(map(self.range_to_string, range_list), ",") - - def range_to_string(self, (c1, c2)): - if c1 == c2: - return repr(c1) - else: - return "%s..%s" % (repr(c1), repr(c2)) -## -## (Superseded by Machines.FastMachine) -## -## class StateTableMachine: -## """ -## StateTableMachine is an alternative representation of a Machine -## that can be run more efficiently. -## """ -## initial_states = None # {state_name:state_index} -## states = None # [([state] indexed by char code, Action)] - -## special_map = {'bol':256, 'eol':257, 'eof':258} - -## def __init__(self, m): -## """ -## Initialise StateTableMachine from Machine |m|. -## """ -## initial_states = self.initial_states = {} -## states = self.states = [None] -## old_to_new = {} -## i = 1 -## for old_state in m.states: -## new_state = ([0] * 259, old_state.get_action()) -## states.append(new_state) -## old_to_new[old_state] = i # new_state -## i = i + 1 -## for name, old_state in m.initial_states.items(): -## initial_states[name] = old_to_new[old_state] -## for old_state in m.states: -## new_state_index = old_to_new[old_state] -## new_table = states[new_state_index][0] -## transitions = old_state.transitions -## for c, old_targets in transitions.items(): -## if old_targets: -## old_target = old_targets[0] -## new_target_index = old_to_new[old_target] -## if len(c) == 1: -## a = ord(c) -## else: -## a = self.special_map[c] -## new_table[a] = states[new_target_index] - -## def dump(self, f): -## f.write("Plex.StateTableMachine:\n") -## f.write(" Initial states:\n") -## for name, index in self.initial_states.items(): -## f.write(" %s: State %d\n" % ( -## repr(name), id(self.states[index]))) -## for i in xrange(1, len(self.states)): -## table, action = self.states[i] -## f.write(" State %d:" % i) -## if action: -## f.write("%s" % action) -## f.write("\n") -## f.write(" %s\n" % map(id,table)) - - - - - - diff --git a/addons/wiki/Plex/Regexps.py b/addons/wiki/Plex/Regexps.py deleted file mode 100755 index 02c2eda8341..00000000000 --- a/addons/wiki/Plex/Regexps.py +++ /dev/null @@ -1,557 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Regular Expressions -# -#======================================================================= - -import array -import string -import types -from sys import maxint - -import Errors - -# -# Constants -# - -BOL = 'bol' -EOL = 'eol' -EOF = 'eof' - -nl_code = ord('\n') - -# -# Helper functions -# - -def chars_to_ranges(s): - """ - Return a list of character codes consisting of pairs - [code1a, code1b, code2a, code2b,...] which cover all - the characters in |s|. - """ - char_list = list(s) - char_list.sort() - i = 0 - n = len(char_list) - result = [] - while i < n: - code1 = ord(char_list[i]) - code2 = code1 + 1 - i = i + 1 - while i < n and code2 >= ord(char_list[i]): - code2 = code2 + 1 - i = i + 1 - result.append(code1) - result.append(code2) - return result - -def uppercase_range(code1, code2): - """ - If the range of characters from code1 to code2-1 includes any - lower case letters, return the corresponding upper case range. - """ - code3 = max(code1, ord('a')) - code4 = min(code2, ord('z') + 1) - if code3 < code4: - d = ord('A') - ord('a') - return (code3 + d, code4 + d) - else: - return None - -def lowercase_range(code1, code2): - """ - If the range of characters from code1 to code2-1 includes any - upper case letters, return the corresponding lower case range. - """ - code3 = max(code1, ord('A')) - code4 = min(code2, ord('Z') + 1) - if code3 < code4: - d = ord('a') - ord('A') - return (code3 + d, code4 + d) - else: - return None - -def CodeRanges(code_list): - """ - Given a list of codes as returned by chars_to_ranges, return - an RE which will match a character in any of the ranges. - """ - re_list = [] - for i in xrange(0, len(code_list), 2): - re_list.append(CodeRange(code_list[i], code_list[i + 1])) - return apply(Alt, tuple(re_list)) - -def CodeRange(code1, code2): - """ - CodeRange(code1, code2) is an RE which matches any character - with a code |c| in the range |code1| <= |c| < |code2|. - """ - if code1 <= nl_code < code2: - return Alt(RawCodeRange(code1, nl_code), - RawNewline, - RawCodeRange(nl_code + 1, code2)) - else: - return RawCodeRange(code1, code2) - -# -# Abstract classes -# - -class RE: - """RE is the base class for regular expression constructors. - The following operators are defined on REs: - - re1 + re2 is an RE which matches |re1| followed by |re2| - re1 | re2 is an RE which matches either |re1| or |re2| - """ - - nullable = 1 # True if this RE can match 0 input symbols - match_nl = 1 # True if this RE can match a string ending with '\n' - str = None # Set to a string to override the class's __str__ result - - def build_machine(self, machine, initial_state, final_state, - match_bol, nocase): - """ - This method should add states to |machine| to implement this - RE, starting at |initial_state| and ending at |final_state|. - If |match_bol| is true, the RE must be able to match at the - beginning of a line. If nocase is true, upper and lower case - letters should be treated as equivalent. - """ - raise exceptions.UnimplementedMethod("%s.build_machine not implemented" % - self.__class__.__name__) - - def build_opt(self, m, initial_state, c): - """ - Given a state |s| of machine |m|, return a new state - reachable from |s| on character |c| or epsilon. - """ - s = m.new_state() - initial_state.link_to(s) - initial_state.add_transition(c, s) - return s - - def __add__(self, other): - return Seq(self, other) - - def __or__(self, other): - return Alt(self, other) - - def __str__(self): - if self.str: - return self.str - else: - return self.calc_str() - - def check_re(self, num, value): - if not isinstance(value, RE): - self.wrong_type(num, value, "Plex.RE instance") - - def check_string(self, num, value): - if type(value) <> type(''): - self.wrong_type(num, value, "string") - - def check_char(self, num, value): - self.check_string(num, value) - if len(value) <> 1: - raise Errors.PlexValueError("Invalid value for argument %d of Plex.%s." - "Expected a string of length 1, got: %s" % ( - num, self.__class__.__name__, repr(value))) - - def wrong_type(self, num, value, expected): - if type(value) == types.InstanceType: - got = "%s.%s instance" % ( - value.__class__.__module__, value.__class__.__name__) - else: - got = type(value).__name__ - raise Errors.PlexTypeError("Invalid type for argument %d of Plex.%s " - "(expected %s, got %s" % ( - num, self.__class__.__name__, expected, got)) - -# -# Primitive RE constructors -# ------------------------- -# -# These are the basic REs from which all others are built. -# - -## class Char(RE): -## """ -## Char(c) is an RE which matches the character |c|. -## """ - -## nullable = 0 - -## def __init__(self, char): -## self.char = char -## self.match_nl = char == '\n' - -## def build_machine(self, m, initial_state, final_state, match_bol, nocase): -## c = self.char -## if match_bol and c <> BOL: -## s1 = self.build_opt(m, initial_state, BOL) -## else: -## s1 = initial_state -## if c == '\n' or c == EOF: -## s1 = self.build_opt(m, s1, EOL) -## if len(c) == 1: -## code = ord(self.char) -## s1.add_transition((code, code+1), final_state) -## if nocase and is_letter_code(code): -## code2 = other_case_code(code) -## s1.add_transition((code2, code2+1), final_state) -## else: -## s1.add_transition(c, final_state) - -## def calc_str(self): -## return "Char(%s)" % repr(self.char) - -def Char(c): - """ - Char(c) is an RE which matches the character |c|. - """ - if len(c) == 1: - result = CodeRange(ord(c), ord(c) + 1) - else: - result = SpecialSymbol(c) - result.str = "Char(%s)" % repr(c) - return result - -class RawCodeRange(RE): - """ - RawCodeRange(code1, code2) is a low-level RE which matches any character - with a code |c| in the range |code1| <= |c| < |code2|, where the range - does not include newline. For internal use only. - """ - nullable = 0 - match_nl = 0 - range = None # (code, code) - uppercase_range = None # (code, code) or None - lowercase_range = None # (code, code) or None - - def __init__(self, code1, code2): - self.range = (code1, code2) - self.uppercase_range = uppercase_range(code1, code2) - self.lowercase_range = lowercase_range(code1, code2) - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - if match_bol: - initial_state = self.build_opt(m, initial_state, BOL) - initial_state.add_transition(self.range, final_state) - if nocase: - if self.uppercase_range: - initial_state.add_transition(self.uppercase_range, final_state) - if self.lowercase_range: - initial_state.add_transition(self.lowercase_range, final_state) - - def calc_str(self): - return "CodeRange(%d,%d)" % (self.code1, self.code2) - -class _RawNewline(RE): - """ - RawNewline is a low-level RE which matches a newline character. - For internal use only. - """ - nullable = 0 - match_nl = 1 - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - if match_bol: - initial_state = self.build_opt(m, initial_state, BOL) - s = self.build_opt(m, initial_state, EOL) - s.add_transition((nl_code, nl_code + 1), final_state) - -RawNewline = _RawNewline() - - -class SpecialSymbol(RE): - """ - SpecialSymbol(sym) is an RE which matches the special input - symbol |sym|, which is one of BOL, EOL or EOF. - """ - nullable = 0 - match_nl = 0 - sym = None - - def __init__(self, sym): - self.sym = sym - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - # Sequences 'bol bol' and 'bol eof' are impossible, so only need - # to allow for bol if sym is eol - if match_bol and self.sym == EOL: - initial_state = self.build_opt(m, initial_state, BOL) - initial_state.add_transition(self.sym, final_state) - - -class Seq(RE): - """Seq(re1, re2, re3...) is an RE which matches |re1| followed by - |re2| followed by |re3|...""" - - def __init__(self, *re_list): - nullable = 1 - for i in xrange(len(re_list)): - re = re_list[i] - self.check_re(i, re) - nullable = nullable and re.nullable - self.re_list = re_list - self.nullable = nullable - i = len(re_list) - match_nl = 0 - while i: - i = i - 1 - re = re_list[i] - if re.match_nl: - match_nl = 1 - break - if not re.nullable: - break - self.match_nl = match_nl - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - re_list = self.re_list - if len(re_list) == 0: - initial_state.link_to(final_state) - else: - s1 = initial_state - n = len(re_list) - for i in xrange(n): - if i < n - 1: - s2 = m.new_state() - else: - s2 = final_state - re = re_list[i] - re.build_machine(m, s1, s2, match_bol, nocase) - s1 = s2 - match_bol = re.match_nl or (match_bol and re.nullable) - - def calc_str(self): - return "Seq(%s)" % string.join(map(str, self.re_list), ",") - - -class Alt(RE): - """Alt(re1, re2, re3...) is an RE which matches either |re1| or - |re2| or |re3|...""" - - def __init__(self, *re_list): - self.re_list = re_list - nullable = 0 - match_nl = 0 - nullable_res = [] - non_nullable_res = [] - i = 1 - for re in re_list: - self.check_re(i, re) - if re.nullable: - nullable_res.append(re) - nullable = 1 - else: - non_nullable_res.append(re) - if re.match_nl: - match_nl = 1 - i = i + 1 - self.nullable_res = nullable_res - self.non_nullable_res = non_nullable_res - self.nullable = nullable - self.match_nl = match_nl - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - for re in self.nullable_res: - re.build_machine(m, initial_state, final_state, match_bol, nocase) - if self.non_nullable_res: - if match_bol: - initial_state = self.build_opt(m, initial_state, BOL) - for re in self.non_nullable_res: - re.build_machine(m, initial_state, final_state, 0, nocase) - - def calc_str(self): - return "Alt(%s)" % string.join(map(str, self.re_list), ",") - - -class Rep1(RE): - """Rep1(re) is an RE which matches one or more repetitions of |re|.""" - - def __init__(self, re): - self.check_re(1, re) - self.re = re - self.nullable = re.nullable - self.match_nl = re.match_nl - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - s1 = m.new_state() - s2 = m.new_state() - initial_state.link_to(s1) - self.re.build_machine(m, s1, s2, match_bol or self.re.match_nl, nocase) - s2.link_to(s1) - s2.link_to(final_state) - - def calc_str(self): - return "Rep1(%s)" % self.re - - -class SwitchCase(RE): - """ - SwitchCase(re, nocase) is an RE which matches the same strings as RE, - but treating upper and lower case letters according to |nocase|. If - |nocase| is true, case is ignored, otherwise it is not. - """ - re = None - nocase = None - - def __init__(self, re, nocase): - self.re = re - self.nocase = nocase - self.nullable = re.nullable - self.match_nl = re.match_nl - - def build_machine(self, m, initial_state, final_state, match_bol, nocase): - self.re.build_machine(m, initial_state, final_state, match_bol, - self.nocase) - - def calc_str(self): - if self.nocase: - name = "NoCase" - else: - name = "Case" - return "%s(%s)" % (name, self.re) - -# -# Composite RE constructors -# ------------------------- -# -# These REs are defined in terms of the primitive REs. -# - -Empty = Seq() -Empty.__doc__ = \ - """ - Empty is an RE which matches the empty string. - """ -Empty.str = "Empty" - -def Str1(s): - """ - Str1(s) is an RE which matches the literal string |s|. - """ - result = apply(Seq, tuple(map(Char, s))) - result.str = "Str(%s)" % repr(s) - return result - -def Str(*strs): - """ - Str(s) is an RE which matches the literal string |s|. - Str(s1, s2, s3, ...) is an RE which matches any of |s1| or |s2| or |s3|... - """ - if len(strs) == 1: - return Str1(strs[0]) - else: - result = apply(Alt, tuple(map(Str1, strs))) - result.str = "Str(%s)" % string.join(map(repr, strs), ",") - return result - -def Any(s): - """ - Any(s) is an RE which matches any character in the string |s|. - """ - #result = apply(Alt, tuple(map(Char, s))) - result = CodeRanges(chars_to_ranges(s)) - result.str = "Any(%s)" % repr(s) - return result - -def AnyBut(s): - """ - AnyBut(s) is an RE which matches any character (including - newline) which is not in the string |s|. - """ - ranges = chars_to_ranges(s) - ranges.insert(0, -maxint) - ranges.append(maxint) - result = CodeRanges(ranges) - result.str = "AnyBut(%s)" % repr(s) - return result - -AnyChar = AnyBut("") -AnyChar.__doc__ = \ - """ - AnyChar is an RE which matches any single character (including a newline). - """ -AnyChar.str = "AnyChar" - -def Range(s1, s2 = None): - """ - Range(c1, c2) is an RE which matches any single character in the range - |c1| to |c2| inclusive. - Range(s) where |s| is a string of even length is an RE which matches - any single character in the ranges |s[0]| to |s[1]|, |s[2]| to |s[3]|,... - """ - if s2: - result = CodeRange(ord(s1), ord(s2) + 1) - result.str = "Range(%s,%s)" % (s1, s2) - else: - ranges = [] - for i in range(0, len(s1), 2): - ranges.append(CodeRange(ord(s1[i]), ord(s1[i+1]) + 1)) - result = apply(Alt, tuple(ranges)) - result.str = "Range(%s)" % repr(s1) - return result - -def Opt(re): - """ - Opt(re) is an RE which matches either |re| or the empty string. - """ - result = Alt(re, Empty) - result.str = "Opt(%s)" % re - return result - -def Rep(re): - """ - Rep(re) is an RE which matches zero or more repetitions of |re|. - """ - result = Opt(Rep1(re)) - result.str = "Rep(%s)" % re - return result - -def NoCase(re): - """ - NoCase(re) is an RE which matches the same strings as RE, but treating - upper and lower case letters as equivalent. - """ - return SwitchCase(re, nocase = 1) - -def Case(re): - """ - Case(re) is an RE which matches the same strings as RE, but treating - upper and lower case letters as distinct, i.e. it cancels the effect - of any enclosing NoCase(). - """ - return SwitchCase(re, nocase = 0) - -# -# RE Constants -# - -Bol = Char(BOL) -Bol.__doc__ = \ - """ - Bol is an RE which matches the beginning of a line. - """ -Bol.str = "Bol" - -Eol = Char(EOL) -Eol.__doc__ = \ - """ - Eol is an RE which matches the end of a line. - """ -Eol.str = "Eol" - -Eof = Char(EOF) -Eof.__doc__ = \ - """ - Eof is an RE which matches the end of the file. - """ -Eof.str = "Eof" - diff --git a/addons/wiki/Plex/Scanners.py b/addons/wiki/Plex/Scanners.py deleted file mode 100755 index 6278d88ba4d..00000000000 --- a/addons/wiki/Plex/Scanners.py +++ /dev/null @@ -1,377 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# -# Scanning an input stream -# -#======================================================================= - -import Errors -from Regexps import BOL, EOL, EOF - -class Scanner: - """ - A Scanner is used to read tokens from a stream of characters - using the token set specified by a Plex.Lexicon. - - Constructor: - - Scanner(lexicon, stream, name = '') - - See the docstring of the __init__ method for details. - - Methods: - - See the docstrings of the individual methods for more - information. - - read() --> (value, text) - Reads the next lexical token from the stream. - - position() --> (name, line, col) - Returns the position of the last token read using the - read() method. - - begin(state_name) - Causes scanner to change state. - - produce(value [, text]) - Causes return of a token value to the caller of the - Scanner. - - """ - - lexicon = None # Lexicon - stream = None # file-like object - name = '' - buffer = '' - buf_start_pos = 0 # position in input of start of buffer - next_pos = 0 # position in input of next char to read - cur_pos = 0 # position in input of current char - cur_line = 1 # line number of current char - cur_line_start = 0 # position in input of start of current line - start_pos = 0 # position in input of start of token - start_line = 0 # line number of start of token - start_col = 0 # position in line of start of token - text = None # text of last token read - initial_state = None # Node - state_name = '' # Name of initial state - queue = None # list of tokens to be returned - trace = 0 - - def __init__(self, lexicon, stream, name = ''): - """ - Scanner(lexicon, stream, name = '') - - |lexicon| is a Plex.Lexicon instance specifying the lexical tokens - to be recognised. - - |stream| can be a file object or anything which implements a - compatible read() method. - - |name| is optional, and may be the name of the file being - scanned or any other identifying string. - """ - self.lexicon = lexicon - self.stream = stream - self.name = name - self.queue = [] - self.initial_state = None - self.begin('') - self.next_pos = 0 - self.cur_pos = 0 - self.cur_line_start = 0 - self.cur_char = BOL - self.input_state = 1 - - def read(self): - """ - Read the next lexical token from the stream and return a - tuple (value, text), where |value| is the value associated with - the token as specified by the Lexicon, and |text| is the actual - string read from the stream. Returns (None, '') on end of file. - """ - queue = self.queue - while not queue: - self.text, action = self.scan_a_token() - if action is None: - self.produce(None) - self.eof() - else: - value = action.perform(self, self.text) - if value is not None: - self.produce(value) - result = queue[0] - del queue[0] - return result - - def scan_a_token(self): - """ - Read the next input sequence recognised by the machine - and return (text, action). Returns ('', None) on end of - file. - """ - self.start_pos = self.cur_pos - self.start_line = self.cur_line - self.start_col = self.cur_pos - self.cur_line_start -# if self.trace: -# action = self.run_machine() -# else: -# action = self.run_machine_inlined() - action = self.run_machine_inlined() - if action: - if self.trace: - print "Scanner: read: Performing", action, "%d:%d" % ( - self.start_pos, self.cur_pos) - base = self.buf_start_pos - text = self.buffer[self.start_pos - base : self.cur_pos - base] - return (text, action) - else: - if self.cur_pos == self.start_pos: - if self.cur_char == EOL: - self.next_char() - if not self.cur_char or self.cur_char == EOF: - return ('', None) - raise Errors.UnrecognizedInput(self, self.state_name) - - def run_machine(self): - """ - Run the machine until no more transitions are possible. - """ - self.state = self.initial_state - self.backup_state = None - while self.transition(): - pass - return self.back_up() - - def run_machine_inlined(self): - """ - Inlined version of run_machine for speed. - """ - state = self.initial_state - cur_pos = self.cur_pos - cur_line = self.cur_line - cur_line_start = self.cur_line_start - cur_char = self.cur_char - input_state = self.input_state - next_pos = self.next_pos - buffer = self.buffer - buf_start_pos = self.buf_start_pos - buf_len = len(buffer) - backup_state = None - trace = self.trace - while 1: - if trace: #TRACE# - print "State %d, %d/%d:%s -->" % ( #TRACE# - state['number'], input_state, cur_pos, repr(cur_char)), #TRACE# - # Begin inlined self.save_for_backup() - #action = state.action #@slow - action = state['action'] #@fast - if action: - backup_state = ( - action, cur_pos, cur_line, cur_line_start, cur_char, input_state, next_pos) - # End inlined self.save_for_backup() - c = cur_char - #new_state = state.new_state(c) #@slow - new_state = state.get(c, -1) #@fast - if new_state == -1: #@fast - new_state = c and state.get('else') #@fast - if new_state: - if trace: #TRACE# - print "State %d" % new_state['number'] #TRACE# - state = new_state - # Begin inlined: self.next_char() - if input_state == 1: - cur_pos = next_pos - # Begin inlined: c = self.read_char() - buf_index = next_pos - buf_start_pos - if buf_index < buf_len: - c = buffer[buf_index] - next_pos = next_pos + 1 - else: - discard = self.start_pos - buf_start_pos - data = self.stream.read(0x1000) - buffer = self.buffer[discard:] + data - self.buffer = buffer - buf_start_pos = buf_start_pos + discard - self.buf_start_pos = buf_start_pos - buf_len = len(buffer) - buf_index = buf_index - discard - if data: - c = buffer[buf_index] - next_pos = next_pos + 1 - else: - c = '' - # End inlined: c = self.read_char() - if c == '\n': - cur_char = EOL - input_state = 2 - elif not c: - cur_char = EOL - input_state = 4 - else: - cur_char = c - elif input_state == 2: - cur_char = '\n' - input_state = 3 - elif input_state == 3: - cur_line = cur_line + 1 - cur_line_start = cur_pos = next_pos - cur_char = BOL - input_state = 1 - elif input_state == 4: - cur_char = EOF - input_state = 5 - else: # input_state = 5 - cur_char = '' - # End inlined self.next_char() - else: # not new_state - if trace: #TRACE# - print "blocked" #TRACE# - # Begin inlined: action = self.back_up() - if backup_state: - (action, cur_pos, cur_line, cur_line_start, - cur_char, input_state, next_pos) = backup_state - else: - action = None - break # while 1 - # End inlined: action = self.back_up() - self.cur_pos = cur_pos - self.cur_line = cur_line - self.cur_line_start = cur_line_start - self.cur_char = cur_char - self.input_state = input_state - self.next_pos = next_pos - if trace: #TRACE# - if action: #TRACE# - print "Doing", action #TRACE# - return action - -# def transition(self): -# self.save_for_backup() -# c = self.cur_char -# new_state = self.state.new_state(c) -# if new_state: -# if self.trace: -# print "Scanner: read: State %d: %s --> State %d" % ( -# self.state.number, repr(c), new_state.number) -# self.state = new_state -# self.next_char() -# return 1 -# else: -# if self.trace: -# print "Scanner: read: State %d: %s --> blocked" % ( -# self.state.number, repr(c)) -# return 0 - -# def save_for_backup(self): -# action = self.state.get_action() -# if action: -# if self.trace: -# print "Scanner: read: Saving backup point at", self.cur_pos -# self.backup_state = ( -# action, self.cur_pos, self.cur_line, self.cur_line_start, -# self.cur_char, self.input_state, self.next_pos) - -# def back_up(self): -# backup_state = self.backup_state -# if backup_state: -# (action, self.cur_pos, self.cur_line, self.cur_line_start, -# self.cur_char, self.input_state, self.next_pos) = backup_state -# if self.trace: -# print "Scanner: read: Backing up to", self.cur_pos -# return action -# else: -# return None - - def next_char(self): - input_state = self.input_state - if self.trace: - print "Scanner: next:", " "*20, "[%d] %d" % (input_state, self.cur_pos), - if input_state == 1: - self.cur_pos = self.next_pos - c = self.read_char() - if c == '\n': - self.cur_char = EOL - self.input_state = 2 - elif not c: - self.cur_char = EOL - self.input_state = 4 - else: - self.cur_char = c - elif input_state == 2: - self.cur_char = '\n' - self.input_state = 3 - elif input_state == 3: - self.cur_line = self.cur_line + 1 - self.cur_line_start = self.cur_pos = self.next_pos - self.cur_char = BOL - self.input_state = 1 - elif input_state == 4: - self.cur_char = EOF - self.input_state = 5 - else: # input_state = 5 - self.cur_char = '' - if self.trace: - print "--> [%d] %d %s" % (input_state, self.cur_pos, repr(self.cur_char)) - -# def read_char(self): -# """ -# Get the next input character, filling the buffer if necessary. -# Returns '' at end of file. -# """ -# next_pos = self.next_pos -# buf_index = next_pos - self.buf_start_pos -# if buf_index == len(self.buffer): -# discard = self.start_pos - self.buf_start_pos -# data = self.stream.read(0x1000) -# self.buffer = self.buffer[discard:] + data -# self.buf_start_pos = self.buf_start_pos + discard -# buf_index = buf_index - discard -# if not data: -# return '' -# c = self.buffer[buf_index] -# self.next_pos = next_pos + 1 -# return c - - def position(self): - """ - Return a tuple (name, line, col) representing the location of - the last token read using the read() method. |name| is the - name that was provided to the Scanner constructor; |line| - is the line number in the stream (1-based); |col| is the - position within the line of the first character of the token - (0-based). - """ - return (self.name, self.start_line, self.start_col) - - def begin(self, state_name): - """Set the current state of the scanner to the named state.""" - self.initial_state = ( - self.lexicon.get_initial_state(state_name)) - self.state_name = state_name - - def produce(self, value, text = None): - """ - Called from an action procedure, causes |value| to be returned - as the token value from read(). If |text| is supplied, it is - returned in place of the scanned text. - - produce() can be called more than once during a single call to an action - procedure, in which case the tokens are queued up and returned one - at a time by subsequent calls to read(), until the queue is empty, - whereupon scanning resumes. - """ - if text is None: - text = self.text - self.queue.append((value, text)) - - def eof(self): - """ - Override this method if you want something to be done at - end of file. - """ - -# For backward compatibility: -setattr(Scanner, "yield", Scanner.produce) diff --git a/addons/wiki/Plex/Timing.py b/addons/wiki/Plex/Timing.py deleted file mode 100755 index f47c5c89de7..00000000000 --- a/addons/wiki/Plex/Timing.py +++ /dev/null @@ -1,22 +0,0 @@ -# -# Get time in platform-dependent way -# - -import os -from sys import platform, exit, stderr - -if platform == 'mac': - import MacOS - def time(): - return MacOS.GetTicks() / 60.0 - timekind = "real" -elif hasattr(os, 'times'): - def time(): - t = os.times() - return t[0] + t[1] - timekind = "cpu" -else: - stderr.write( - "Don't know how to get time on platform %s\n" % repr(platform)) - exit(1) - diff --git a/addons/wiki/Plex/Traditional.py b/addons/wiki/Plex/Traditional.py deleted file mode 100755 index b3148c1ec0e..00000000000 --- a/addons/wiki/Plex/Traditional.py +++ /dev/null @@ -1,154 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -# Traditional Regular Expression Syntax -# -#======================================================================= - -from Regexps import * -from Errors import PlexError - -class RegexpSyntaxError(PlexError): - pass - -def re(s): - """ - Convert traditional string representation of regular expression |s| - into Plex representation. - """ - return REParser(s).parse_re() - -class REParser: - - def __init__(self, s): - self.s = s - self.i = -1 - self.end = 0 - self.next() - - def parse_re(self): - re = self.parse_alt() - if not self.end: - self.error("Unexpected %s" % repr(self.c)) - return re - - def parse_alt(self): - """Parse a set of alternative regexps.""" - re = self.parse_seq() - if self.c == '|': - re_list = [re] - while self.c == '|': - self.next() - re_list.append(self.parse_seq()) - re = apply(Alt, tuple(re_list)) - return re - - def parse_seq(self): - """Parse a sequence of regexps.""" - re_list = [] - while not self.end and not self.c in "|)": - re_list.append(self.parse_mod()) - return apply(Seq, tuple(re_list)) - - def parse_mod(self): - """Parse a primitive regexp followed by *, +, ? modifiers.""" - re = self.parse_prim() - while not self.end and self.c in "*+?": - if self.c == '*': - re = Rep(re) - elif self.c == '+': - re = Rep1(re) - else: # self.c == '?' - re = Opt(re) - self.next() - return re - - def parse_prim(self): - """Parse a primitive regexp.""" - c = self.get() - if c == '.': - re = AnyBut("\n") - elif c == '^': - re = Bol - elif c == '$': - re = Eol - elif c == '(': - re = self.parse_alt() - self.expect(')') - elif c == '[': - re = self.parse_charset() - self.expect(']') - else: - if c == '\\': - c = self.get() - re = Char(c) - return re - - def parse_charset(self): - """Parse a charset. Does not include the surrounding [].""" - char_list = [] - invert = 0 - if self.c == '^': - invert = 1 - self.next() - if self.c == ']': - char_list.append(']') - self.next() - while not self.end and self.c <> ']': - c1 = self.get() - if self.c == '-' and self.lookahead(1) <> ']': - self.next() - c2 = self.get() - for a in xrange(ord(c1), ord(c2) + 1): - char_list.append(chr(a)) - else: - char_list.append(c1) - chars = string.join(char_list, "") - if invert: - return AnyBut(chars) - else: - return Any(chars) - - def next(self): - """Advance to the next char.""" - s = self.s - i = self.i = self.i + 1 - if i < len(s): - self.c = s[i] - else: - self.c = '' - self.end = 1 - - def get(self): - if self.end: - self.error("Premature end of string") - c = self.c - self.next() - return c - - def lookahead(self, n): - """Look ahead n chars.""" - j = self.i + n - if j < len(self.s): - return self.s[j] - else: - return '' - - def expect(self, c): - """ - Expect to find character |c| at current position. - Raises an exception otherwise. - """ - if self.c == c: - self.next() - else: - self.error("Missing %s" % repr(c)) - - def error(self, mess): - """Raise exception to signal syntax error in regexp.""" - raise RegexpSyntaxError("Syntax error in regexp %s at position %d: %s" % ( - repr(self.s), self.i, mess)) - - - diff --git a/addons/wiki/Plex/Transitions.py b/addons/wiki/Plex/Transitions.py deleted file mode 100755 index 5b0d4fca6cf..00000000000 --- a/addons/wiki/Plex/Transitions.py +++ /dev/null @@ -1,252 +0,0 @@ -# -# Plex - Transition Maps -# -# This version represents state sets direcly as dicts -# for speed. -# - -from copy import copy -import string -from sys import maxint -from types import TupleType - -class TransitionMap: - """ - A TransitionMap maps an input event to a set of states. - An input event is one of: a range of character codes, - the empty string (representing an epsilon move), or one - of the special symbols BOL, EOL, EOF. - - For characters, this implementation compactly represents - the map by means of a list: - - [code_0, states_0, code_1, states_1, code_2, states_2, - ..., code_n-1, states_n-1, code_n] - - where |code_i| is a character code, and |states_i| is a - set of states corresponding to characters with codes |c| - in the range |code_i| <= |c| <= |code_i+1|. - - The following invariants hold: - n >= 1 - code_0 == -maxint - code_n == maxint - code_i < code_i+1 for i in 0..n-1 - states_0 == states_n-1 - - Mappings for the special events '', BOL, EOL, EOF are - kept separately in a dictionary. - """ - - map = None # The list of codes and states - special = None # Mapping for special events - - def __init__(self, map = None, special = None): - if not map: - map = [-maxint, {}, maxint] - if not special: - special = {} - self.map = map - self.special = special - #self.check() ### - - def add(self, event, new_state, - TupleType = TupleType): - """ - Add transition to |new_state| on |event|. - """ - if type(event) == TupleType: - code0, code1 = event - i = self.split(code0) - j = self.split(code1) - map = self.map - while i < j: - map[i + 1][new_state] = 1 - i = i + 2 - else: - self.get_special(event)[new_state] = 1 - - def add_set(self, event, new_set, - TupleType = TupleType): - """ - Add transitions to the states in |new_set| on |event|. - """ - if type(event) == TupleType: - code0, code1 = event - i = self.split(code0) - j = self.split(code1) - map = self.map - while i < j: - map[i + 1].update(new_set) - i = i + 2 - else: - self.get_special(event).update(new_set) - - def get_epsilon(self): - """ - Return the mapping for epsilon, or None. - """ - return self.special.get('') - - def items(self, - len = len): - """ - Return the mapping as a list of ((code1, code2), state_set) and - (special_event, state_set) pairs. - """ - result = [] - map = self.map - else_set = map[1] - i = 0 - n = len(map) - 1 - code0 = map[0] - while i < n: - set = map[i + 1] - code1 = map[i + 2] - if set or else_set: - result.append(((code0, code1), set)) - code0 = code1 - i = i + 2 - for event, set in self.special.items(): - if set: - result.append((event, set)) - return result - - # ------------------- Private methods -------------------- - - def split(self, code, - len = len, maxint = maxint): - """ - Search the list for the position of the split point for |code|, - inserting a new split point if necessary. Returns index |i| such - that |code| == |map[i]|. - """ - # We use a funky variation on binary search. - map = self.map - hi = len(map) - 1 - # Special case: code == map[-1] - if code == maxint: - return hi - # General case - lo = 0 - # loop invariant: map[lo] <= code < map[hi] and hi - lo >= 2 - while hi - lo >= 4: - # Find midpoint truncated to even index - mid = ((lo + hi) / 2) & ~1 - if code < map[mid]: - hi = mid - else: - lo = mid - # map[lo] <= code < map[hi] and hi - lo == 2 - if map[lo] == code: - return lo - else: - map[hi:hi] = [code, map[hi - 1].copy()] - #self.check() ### - return hi - - def get_special(self, event): - """ - Get state set for special event, adding a new entry if necessary. - """ - special = self.special - set = special.get(event, None) - if not set: - set = {} - special[event] = set - return set - - # --------------------- Conversion methods ----------------------- - - def __str__(self): - map_strs = [] - map = self.map - n = len(map) - i = 0 - while i < n: - code = map[i] - if code == -maxint: - code_str = "-inf" - elif code == maxint: - code_str = "inf" - else: - code_str = str(code) - map_strs.append(code_str) - i = i + 1 - if i < n: - map_strs.append(state_set_str(map[i])) - i = i + 1 - special_strs = {} - for event, set in self.special.items(): - special_strs[event] = state_set_str(set) - return "[%s]+%s" % ( - string.join(map_strs, ","), - special_strs - ) - - # --------------------- Debugging methods ----------------------- - - def check(self): - """Check data structure integrity.""" - if not self.map[-3] < self.map[-1]: - print self - assert 0 - - def dump(self, file): - map = self.map - i = 0 - n = len(map) - 1 - while i < n: - self.dump_range(map[i], map[i + 2], map[i + 1], file) - i = i + 2 - for event, set in self.special.items(): - if set: - if not event: - event = 'empty' - self.dump_trans(event, set, file) - - def dump_range(self, code0, code1, set, file): - if set: - if code0 == -maxint: - if code1 == maxint: - k = "any" - else: - k = "< %s" % self.dump_char(code1) - elif code1 == maxint: - k = "> %s" % self.dump_char(code0 - 1) - elif code0 == code1 - 1: - k = self.dump_char(code0) - else: - k = "%s..%s" % (self.dump_char(code0), - self.dump_char(code1 - 1)) - self.dump_trans(k, set, file) - - def dump_char(self, code): - if 0 <= code <= 255: - return repr(chr(code)) - else: - return "chr(%d)" % code - - def dump_trans(self, key, set, file): - file.write(" %s --> %s\n" % (key, self.dump_set(set))) - - def dump_set(self, set): - return state_set_str(set) - -# -# State set manipulation functions -# - -#def merge_state_sets(set1, set2): -# for state in set2.keys(): -# set1[state] = 1 - -def state_set_str(set): - state_list = set.keys() - str_list = [] - for state in state_list: - str_list.append("S%d" % state.number) - return "[%s]" % string.join(str_list, ",") - - - diff --git a/addons/wiki/Plex/__init__.py b/addons/wiki/Plex/__init__.py deleted file mode 100755 index 22b9bba3b8c..00000000000 --- a/addons/wiki/Plex/__init__.py +++ /dev/null @@ -1,40 +0,0 @@ -#======================================================================= -# -# Python Lexical Analyser -# -#======================================================================= - -""" -The Plex module provides lexical analysers with similar capabilities -to GNU Flex. The following classes and functions are exported; -see the attached docstrings for more information. - - Scanner For scanning a character stream under the - direction of a Lexicon. - - Lexicon For constructing a lexical definition - to be used by a Scanner. - - Str, Any, AnyBut, AnyChar, Seq, Alt, Opt, Rep, Rep1, - Bol, Eol, Eof, Empty - - Regular expression constructors, for building pattern - definitions for a Lexicon. - - State For defining scanner states when creating a - Lexicon. - - TEXT, IGNORE, Begin - - Actions for associating with patterns when - creating a Lexicon. -""" - -from Actions import TEXT, IGNORE, Begin -from Lexicons import Lexicon, State -from Regexps import RE, Seq, Alt, Rep1, Empty, Str, Any, AnyBut, AnyChar, Range -from Regexps import Opt, Rep, Bol, Eol, Eof, Case, NoCase -from Scanners import Scanner - - - diff --git a/addons/wiki/Plex/test_tm.py b/addons/wiki/Plex/test_tm.py deleted file mode 100755 index e08c9e68f93..00000000000 --- a/addons/wiki/Plex/test_tm.py +++ /dev/null @@ -1,24 +0,0 @@ -import sys -sys.stderr = sys.stdout - -from TransitionMaps import TransitionMap - -m = TransitionMap() -print m - -def add(c, s): - print - print "adding", repr(c), "-->", repr(s) - m.add_transition(c, s) - print m - print "keys:", m.keys() - -add('a','alpha') -add('e', 'eta') -add('f', 'foo') -add('i', 'iota') -add('i', 'imp') -add('eol', 'elephant') - - - diff --git a/addons/wiki/Wiki2Html.py b/addons/wiki/Wiki2Html.py deleted file mode 100755 index 0d84d59af25..00000000000 --- a/addons/wiki/Wiki2Html.py +++ /dev/null @@ -1,332 +0,0 @@ -# Copyright (C) 2006 Samuel Abels, http://debain.org -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2, as -# published by the Free Software Foundation. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -import HTMLParser, re, sys -from WikiParser import WikiParser -from cgi import escape - -class Wiki2Html: - def __init__(self): - self.html = '' - self.buffer = '' - self.counter = 0 - self.in_list = False - self.in_numbered_list = False - self.in_heading = False - self.in_table = False - self.in_cell = False - self.indent_level = 0 - self.url_handler = None - self.wiki_word_handler = None - - - def set_url_handler(self, handler): - """ - Whenever the parser finds a URL in the output, by default it - automatically translates it into a clickable link in the HTML output. - However, if you want more fine-grained control over which URLs are - converted into links, you might want to use this function. - It calls the given handler function before a link is added into the - HTML. The function is passed the URL and the caption. - The handler can the modify the URL and the caption, and pass it - back to the parser. Example handler: - - def url_handler(url, caption): - return (url, 'My Caption') - - The parser uses the returned values to build a link in the HTML. - If URL is None, the item is not linked at all. - """ - self.url_handler = handler - - - def set_wiki_word_handler(self, handler): - """ - Like set_url_handler() but for WikiWords. - Example handler: - - def wiki_word_handler(word): - return (url, word) - - The parser uses the returned values to build a link in the HTML. - If URL is None, the item is not linked at all. - """ - self.wiki_word_handler = handler - - #onclick="openWindow(getURL('/attachment', {model: 'base.wiki', id: id=$id}), {name : 'Attachments'}) - def image(self, text): - image = text.strip() - url = image.split(':')[1] - self.buffer += """ - Please upload Image
\n""" - - def indent(self, level): - self.indent_level = level - - def dedent(self, level): - self.indent_level = level - - - def code_start(self, text): - self.buffer += '
'
-
-
-    def code(self, text):
-        self.buffer += escape(text)
-
-
-    def code_end(self, text):
-        self.buffer += '
\n' - - - def title1_start(self, text): - self.buffer += '

' - - - def title1_end(self, text): - self.buffer += '

' - - - def title2_start(self, text): - self.buffer += '

' - - - def title2_end(self, text): - self.buffer += '

' - - - def title3_start(self, text): - self.buffer += '

' - - - def title3_end(self, text): - self.buffer += '

' - - - def italic_start(self, text): - self.buffer += '' - - - def italic_end(self, text): - self.buffer += '' - - - def bold_start(self, text): - self.buffer += '' - - - def bold_end(self, text): - self.buffer += '' - - - def underline_start(self, text): - self.buffer += '' - - - def underline_end(self, text): - self.buffer += '' - - - def unnumbered_list_start(self, text): - self.buffer += '\n' - self.in_list = False - - - def list_item_start(self, text): - self.buffer += '
  • ' - - - def list_item_end(self, text): - self.__flush(True) - self.buffer += '
    • \n' - - - def table_start(self, text): - self.in_table = True - self.counter = 0 - self.buffer += '\n' - - - def heading_start(self, text): - self.in_heading = True - self.row_start(text) - - - def row_start(self, text): - self.buffer += '' - - - def cell_start(self, text): - self.in_cell = True - attribs = '' - if len(text) - 1 > 1: - attribs += ' colspan=%i' % (len(text) - 1) - if self.in_heading: - self.buffer += '' % attribs - else: - self.buffer += '' % attribs - self.__flush(True) - - - def cell_end(self, text): - # If the cell contains only a hash, replace it by a counter. - if self.buffer.strip() == '#': - self.counter += 1 - self.buffer = str(self.counter) + '.' - self.__flush(True) - self.in_cell = False - if self.in_heading: - self.html += '' - else: - self.html += '' - self.html += '\n' + (' ' * self.indent_level) - - - def row_end(self, text): - self.buffer += '\n' + (' ' * self.indent_level) - - - def heading_end(self, text): - self.in_heading = False - self.row_end(text) - - - def table_end(self, text): - self.in_table = False - self.buffer += '
    \n' - - - def text(self, text): - self.buffer += escape(text).replace('\n', '
    \n') - - - def newline(self, text): - if (self.in_table - or self.in_list - or (self.buffer[-5:-2] == '') - or (self.buffer[-6:-3] == '')): - self.buffer += '\n' - return - self.buffer += '
    \n' - - - def link(self, text): - text = text[1:-1] - pos = text.find('-') - if pos == -1: - url = text - caption = url - else: - url = text[:pos] - caption = text[pos + 1:] - if self.url_handler is not None: - (url, caption) = self.url_handler(url.strip()+"'", caption) - url = escape(url) - caption = escape(caption) - if url is None: - self.buffer += caption - else: - if url.strip().startswith('http') or url.strip().startswith('www') or url.strip().startswith('https') or url.strip().startswith('frp'): - self.buffer += '%s' % (url.strip(), caption) - else: - self.buffer += '%s' % ("/wiki?id="+url.strip()+"&title='" + caption.strip() + "'" , caption ) - - def wiki_word(self, text): - if text.startswith('->'): - text = text[2:] - url = text - caption = text - if self.wiki_word_handler is not None: - (url, caption) = self.wiki_word_handler("/wiki?id='"+url.strip()+"'", caption) - url = escape(url) - caption = escape(caption) - if url is None: - self.buffer += caption - else: - self.buffer += '%s' % ("/wiki?id='"+url.strip()+"'", caption) - - - def not_wiki_word(self, text): - self.buffer += escape(text) - - - def __flush(self, strip = False): - if strip: - self.html += self.buffer.strip() - else: - self.html += self.buffer - self.buffer = '' - - - def read(self, filename): - infile = open(filename, 'U') - parser = WikiParser(infile, filename) - nonecount = 0 - self.html = '' - while True: - token = parser.read() - position = parser.position() - if token[0] is None: - nonecount += 1 # This is because Plex is broken. - if nonecount >= 2: - break - try: - method = getattr(self, token[0]) - except: - method = None - if method is not None: - method(token[1]) - infile.close() - self.__flush() - - -if __name__ == '__main__': - import unittest - - class Wiki2HtmlTest(unittest.TestCase): - def runTest(self): - # Read the entire file into one string. - filename = 'markup.txt' - infile = open(filename, 'r') - in_str = infile.read() - infile.close() - - # Parse the file. - parser = Wiki2Html() - parser.read(filename) - html = parser.html - print html - - # Now *that's* a poor test, huh? For a better test, look - # at the test in Html2Wiki.py. - assert len(html) > 1000 - - testcase = Wiki2HtmlTest() - runner = unittest.TextTestRunner() - runner.run(testcase) diff --git a/addons/wiki/WikiParser.py b/addons/wiki/WikiParser.py deleted file mode 100755 index ea4fbbe9ccb..00000000000 --- a/addons/wiki/WikiParser.py +++ /dev/null @@ -1,417 +0,0 @@ -# Copyright (C) 2006 Samuel Abels, http://debain.org -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2, as -# published by the Free Software Foundation. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -import sys, string -sys.path.append('..') -from Plex import * - -# Single char definitions. -letter = Range('AZaz') -digit = Range('09') -spaces = Any(" \t\r\n") -nl = Str("\n") | Eof -not_nl = AnyBut("\r\n") -dash = Str('-') -colon = Str(':') -hash = Str('#') -at = Str('@') -equal = Str('=') -star = Str('*') -slash = Str('/') -o_bracket = Str('{') -c_bracket = Str('}') -underscore = Str('_') -dot = Str('.') -punctuation = Any('.!?,;:') -quotes = Any('\'"') - -# Single word definitions. -name = letter + Rep(letter | digit) -file_name = Rep1(letter | digit | dash | underscore | dot) -wiki_force = Str('->') + name -wiki_word = Range('AZ') + name + Range('AZ') + name -not_w_word = Str('!') + wiki_word -indentation = Rep(Str(' ')) | Rep(Str("\t")) -variable = letter + Rep(letter | digit | Str('_')) + Rep(letter | digit) -proto = Alt(Str('http'), Str('https'), Str('ftp'), Str('mailto')) -login = file_name + Opt(colon + file_name) -host = name + Rep(letter | digit | dash | underscore | dot) + name -path = Opt(slash) + file_name + Rep(slash + file_name) + Opt(slash) -arg_value = Rep1(letter | digit | dash | underscore | dot | Str('%')) -arg = file_name + equal + Opt(arg_value) -args = Str('?') + arg + Rep(Str('&') + arg) -path_args = path + Opt(args) -url = proto + colon + Str('//') + Opt(login + at) + host + Opt(path_args) -code = Str('#Text') + nl -code_end = Str('#End') + nl - -# Markup. -line = Rep(not_nl) + nl -blank_line = indentation + nl -words = Rep1(letter | digit | spaces) -list_item = Bol + Alt(hash, star) + Str(' ') -italic_start = Alt(Bol, spaces) + slash -italic_end = slash + Alt(Eol, spaces, punctuation) -phrase = Rep1(words | dash | at | punctuation | slash | quotes| hash | Str('$')) -title1 = equal + phrase + equal -title2 = equal + equal + phrase + equal + equal -title3 = equal + equal + equal + phrase + equal + equal + equal -heading = Str('#Heading') + nl -row = Str('#Row') + nl -cell = Rep1(Str('|')) + Str(' ') -internal_link = Str('[') + url + Opt(spaces + phrase) + Str(']') -external_link = Str('[') + path_args + Opt(spaces + phrase) + Str(']') -image = Str('Attach') + colon + Opt(phrase) + nl - -class WikiParser(Scanner): - def __init__(self, file, filename): - Scanner.__init__(self, self.lexicon, file, filename) - self.my_buffer = '' - self.indentation_stack = [0] - self.bracket_nesting_level = 0 - self.in_italic = False - self.in_bold = False - self.in_underline = False - self.in_list = False - self.in_list_item = False - self.in_table = False - self.in_heading = False - self.in_row = False - self.in_cell = False - self.begin('indent') - - def _buffer_flush(self): - indent = self._get_current_indent_level() - #print "_buffer_flush (%i): '%s'" % (indent, self.my_buffer) - if self.my_buffer == '': - return - if self.my_buffer == '\n': - self.produce('newline', '\n') - else: - self.produce('text', self.my_buffer) - #print "Flush produced" - self.my_buffer = '' - - def _newline_action(self, text): - #print '_newline_action' - self._buffer_flush() - self.produce('newline', text) - if self.bracket_nesting_level == 0: - self.begin('indent') - - def _indentation_action(self, text): - #print '_indentation_action' - self.my_buffer += text - self._buffer_flush() - current_level = self._get_current_indent_level() - new_level = len(text) - if new_level > current_level: - self._indent_to(new_level) - elif new_level < current_level: - self._dedent_to(new_level) - self.begin('') - - def _indent_to(self, new_level): - self.indentation_stack.append(new_level) - self.produce('indent', new_level) - - def _dedent_to(self, new_level): - while new_level < self._get_current_indent_level(): - self.indentation_stack.pop() - self.produce('dedent', self._get_current_indent_level()) - - def _get_current_indent_level(self): - return self.indentation_stack[-1] - - def _code_start(self, text): - #print '_code_start: ' + text - self._buffer_flush() - self.produce('code_start', text) - self.begin('code') - - def _code(self, text): - #print '_code: ' + text - self.my_buffer += text - - def _code_end(self, text): - #print '_code_end: ' + text - if self.my_buffer != '': - self.produce('code', self.my_buffer) - self.my_buffer = '' - self.produce('code_end', text) - self.begin('') - - def _title1(self, text): - #print '_title1: ' + text - self._buffer_flush() - self.produce('title1_start', text[0]) - self.my_buffer += text[1:-1] - self._buffer_flush() - self.produce('title1_end', text[-1]) - - def _title2(self, text): - #print '_title2: ' + text - self._buffer_flush() - self.produce('title2_start', text[0:2]) - self.my_buffer += text[2:-2] - self._buffer_flush() - self.produce('title2_end', text[-2:]) - - def _title3(self, text): - #print '_title3: ' + text - self._buffer_flush() - self.produce('title3_start', text[0:3]) - self.my_buffer += text[3:-3] - self._buffer_flush() - self.produce('title3_end', text[-3:]) - - def _italic_start(self, text): - #print '_italic_start "%s"' % text - if text[0] != '/': - self.my_buffer += text[0] - self._buffer_flush() - self.in_italic = True - self.produce('italic_start', text[-1]) - - def _italic_end(self, text): - #print '_italic_end' - self._buffer_flush() - self.produce('italic_end', text[0]) - self.in_italic = False - self.my_buffer += text[1] - - def _bold(self, text): - #print '_bold' - self._buffer_flush() - if self.in_bold: - self.produce('bold_end', text) - self.in_bold = False - else: - self.in_bold = True - self.produce('bold_start', text) - - def _underline(self, text): - #print '_underline' - self._buffer_flush() - if self.in_underline: - self.produce('underline_end', text) - self.in_underline = False - else: - self.in_underline = True - self.produce('underline_start', text) - - def _list_item(self, text): - self._buffer_flush() - if not self.in_list: - if text.startswith('#'): - self.produce('numbered_list_start', '') - elif text.startswith('*'): - self.produce('unnumbered_list_start', '') - self.in_list = True - if self.in_list_item: - self._list_item_end() - self.in_list_item = True - self.produce('list_item_start') - - def _list_item_end(self): - self.in_list_item = False - self.produce('list_item_end', '') - - def _list_end(self): - if self.in_list_item: - self._list_item_end() - self.in_list = False - self.produce('list_end', '') - - def _heading_start(self, text): - self._buffer_flush() - if not self.in_table: - self.produce('table_start', '') - self.in_table = True - if self.in_heading: - self._heading_end() - self.in_heading = True - self.produce('heading_start', text[:-1]) - self._newline_action(text[-1]) - - def _row_start(self, text): - self._buffer_flush() - if not self.in_table: - self.produce('table_start', '') - self.in_table = True - if self.in_heading: - self._heading_end() - if self.in_row: - self._row_end() - self.in_row = True - self.produce('row_start', text[:-1]) - self._newline_action(text[-1]) - - def _cell_start(self, text): - self._buffer_flush() - if not self.in_heading and not self.in_row: - self._text(text) - return - if self.in_cell: - self._cell_end() - self.in_cell = True - self.produce('cell_start') - - def _cell_end(self): - self.in_cell = False - self.produce('cell_end', '') - - def _row_end(self): - if self.in_cell: - self._cell_end() - self.in_row = False - self.produce('row_end', '') - - def _heading_end(self): - if self.in_cell: - self._cell_end() - self.in_heading = False - self.produce('heading_end', '') - - def _table_end(self): - if self.in_heading: - self._heading_end() - if self.in_row: - self._row_end() - self.in_table = False - self.produce('table_end', '') - - def _link(self, text): - self._buffer_flush() - self.produce('link', text) - - def _image(self, text): - self._buffer_flush() - self.produce('image', text) - - def _wiki_word(self, text): - self._buffer_flush() - self.produce('wiki_word', text) - - def _not_wiki_word(self, text): - self._buffer_flush() - self.produce('not_wiki_word_intro', text[0]) - self.produce('not_wiki_word', text[1:]) - - def _open_bracket_action(self, text): - #print '_open_bracket_action' - self.my_buffer += text - self.bracket_nesting_level = self.bracket_nesting_level + 1 - - def _close_bracket_action(self, text): - #print '_close_bracket_action' - self.my_buffer += text - self.bracket_nesting_level = self.bracket_nesting_level - 1 - - def _blank_line(self, text): - self._dedent_to(0) - self.my_buffer += text - if self.in_list: - self._list_end() - if self.in_table: - self._table_end() - self._buffer_flush() - - def _text(self, text): - #print "Char: '%s'" % text - self.my_buffer += text - - def eof(self): - #print "EOF" - self._blank_line('') - - lexicon = Lexicon([ - # Handle whitespace and indentation. - (nl, _newline_action), - State('indent', [ - (blank_line, _blank_line), - (indentation, _indentation_action) - ]), - - # Preformatted text/code. - (code, _code_start), - State('code', [ - (code_end, _code_end), - (AnyChar, _code) - ]), - - # Brackets. - (o_bracket, _open_bracket_action), - (c_bracket, _close_bracket_action), - - # Styles. - (list_item, _list_item), - (title1, _title1), - (title2, _title2), - (title3, _title3), - (star, _bold), - (underscore, _underline), - (italic_start, _italic_start), - (italic_end, _italic_end), - - # Tables. - (heading, _heading_start), - (row, _row_start), - (cell, _cell_start), - - # Other. - (internal_link, _link), - (external_link, _link), - (not_w_word, _not_wiki_word), - (wiki_word, _wiki_word), - (wiki_force, _wiki_word), - (AnyChar, _text), - (image, _image) - ]) - - -if __name__ == '__main__': - import unittest - - class ParserTest(unittest.TestCase): - def runTest(self): - # Read the entire file into one string. - filename = 'markup.txt' - infile = open(filename, "U") - in_text = infile.read() - infile.close() - - # Re-open and parse the entire file. - infile = open(filename, "r") - scanner = WikiParser(infile, filename) - content = '' - nonecount = 0 - while True: - token = scanner.read() - position = scanner.position() - if token[0] is None: - nonecount += 1 # This is because Plex is broken. - if nonecount >= 2: - break - #print "Token type: %s, Token: '%s'" % (token[0], token[1]) - if not token[0] in ['indent', 'dedent']: - content += token[1] - - # Make sure that every single string was extracted. - #print content - assert content == in_text - - testcase = ParserTest() - runner = unittest.TextTestRunner() - runner.run(testcase) diff --git a/addons/wiki/__init__.py b/addons/wiki/__init__.py old mode 100755 new mode 100644 index 5001d3c5ac7..98cdc450bae --- a/addons/wiki/__init__.py +++ b/addons/wiki/__init__.py @@ -1,10 +1,2 @@ -__all__ = ['Wiki2Html', - 'Html2Wiki'] -from Wiki2Html import Wiki2Html -from Html2Wiki import Html2Wiki import wiki -#import IndexServer -import os - -os.system("python IndexServer.py") \ No newline at end of file diff --git a/addons/wiki/__terp__.py b/addons/wiki/__terp__.py index 831610cf640..57dc7b3b623 100755 --- a/addons/wiki/__terp__.py +++ b/addons/wiki/__terp__.py @@ -1,12 +1,15 @@ { - "name" : "Wiki Base System", + "name" : "Wiki System", "version" : "1.0", - "author" : "Axelor Sarl", + "author" : "Tiny ERP", "category" : "Generic Modules/Others", - "depends" : ["base", "project"], + "depends" : ["base"], "init_xml" : [], "demo_xml" : [], - "update_xml" : ["wiki_view.xml","wiki_data.xml"], + "update_xml" : [ + "wiki_view.xml", + "wiki_data.xml" + ], "active": False, "installable": True } \ No newline at end of file diff --git a/addons/wiki/config.py b/addons/wiki/config.py deleted file mode 100755 index ce33e652e5e..00000000000 --- a/addons/wiki/config.py +++ /dev/null @@ -1,7 +0,0 @@ -import os - -index_server = "" -index_port = 8000 - -tiny_port = 8069 -tiny_host = 'localhost' diff --git a/addons/wiki/wiki.py b/addons/wiki/wiki.py index a04f671aeee..d2a4e0d39a0 100755 --- a/addons/wiki/wiki.py +++ b/addons/wiki/wiki.py @@ -28,111 +28,63 @@ from osv import fields, osv import time -from Wiki2Html import Wiki2Html -import xmlrpclib -import base64 -import os +#from core.Wiki2Html import Wiki2Html from StringIO import StringIO -import popen2 class Tag(osv.osv): - _name="base.wiki.tag" + _name="wiki.wiki.tag" _description="Wiki" - _rec_name="title" + _columns={ - 'title':fields.char('Title',size=128), + 'name':fields.char('Title',size=128), } Tag() class Wiki(osv.osv): - _name="base.wiki" + _name="wiki.wiki" _description="Wiki" - _rec_name="title" _order = 'model_id' _columns={ - 'title':fields.char('Title', size=128, select=True), - 'last_modify_by':fields.many2one('res.users',"Last Modify By"), + 'name':fields.char('Title', size=128, select=True, required=True), + 'write_uid':fields.many2one('res.users',"Last Modify By"), 'text_area':fields.text("Content", select=True), - 'wiki_create_uid':fields.many2one('res.users','Authour', select=True), - 'wiki_create_date':fields.datetime("Created on", select=True), - 'wiki_write_date':fields.datetime("Last modified", select=True), - 'tags':fields.many2many("base.wiki.tag","wiki_tag_many_id","wiki_id","tag_id","Tags", select=True), - #'forum_id':fields.one2many('base.wiki.forum','wiki_id','Forum Lines'), - 'history_id':fields.one2many('base.wiki.history','history_wiki_id','History Lines'), - 'html':fields.text("Html Data", select=True), + 'create_uid':fields.many2one('res.users','Authour', select=True), + 'create_date':fields.datetime("Created on", select=True), + 'write_date':fields.datetime("Last modified", select=True), + 'tags':fields.char('Tags', size=1024), # many2many("wiki.wiki.tag","wiki_tag_many_id","wiki_id","tag_id","Tags", select=True), + 'history_id':fields.one2many('wiki.wiki.history','history_wiki_id','History Lines'), 'path':fields.char('Page Path',size=128), 'model_id': fields.many2one('ir.model', 'Model id', select=True, ondelete='cascade'), 'res_id': fields.integer("Record Id"), 'minor_edit':fields.boolean('Thisd is a minor edit', select=True), 'summary':fields.char('Summary',size=256, select=True), } - _defaults = { - 'wiki_create_date': lambda *a: time.strftime('%Y-%m-%d %H:%M:%S'), - 'wiki_create_uid': lambda obj,cr,uid,context: uid, - } def __init__(self, cr, pool): super(Wiki, self).__init__(cr, pool) self.oldmodel = None def read(self, cr, uid, cids, fields=None, context=None, load='_classic_read'): - result = super(Wiki, self).read(cr, uid, cids, {}, load='_classic_read') - - if context and context.get('index'): - ids = self.search(cr, uid, [('model_id','!=',False), ('id','in',cids)]) - res = self.read(cr, uid, ids) - - buffer = '' - for rs in res: - if self.oldmodel != rs['model_id'][1] or self.oldmodel == None: - self.oldmodel = rs['model_id'][1] - buffer+= '\n==' + self.pool.get('ir.model').browse(cr, uid, rs['model_id'][0]).name + '==\n' - - rec_url = '/form/view?model=' + rs['model_id'][1] + "&id=" + str(rs['res_id']) - edit_url = '/form/edit?model=' + rs['model_id'][1] + "&id=" + str(rs['res_id']) - buffer+= '#Row\n' - buffer+= '| # | ' + rs['title'] + ' | [' + rs['path'] + ' - wiki]' + ' | [' + rec_url + ' - Browse ] | [' + edit_url + ' - Edit ]\n' - - ids = self.search(cr, uid, [('model_id','=',False), ('id','in',cids)]) - res = self.read(cr, uid, ids) - - if res: - buffer+= '\n==Other Pages==\n' - for rs in res: - - buffer+= '* [' + rs['path'] + ' - ' + rs['title'] + ']\n' - - return [{'html':self.Wiki2Html(buffer)}] - else: - return result - - def Wiki2Html(self, wiki): - fileName = 'data.txt' - file = open(fileName, 'w') - file.write(wiki+'\n\n') - file.close() - - parser = Wiki2Html() - parser.read(fileName) - return parser.html + ids = [] + for id in cids: + if type(id) == type(1): + ids.append(id) + elif type(id) == type(u''): + ids.append(10) + + result = super(Wiki, self).read(cr, uid, ids, fields, None, load='_classic_read') + return result def create(self, cr, uid, vals, context=None): - if vals.get('text_area'): - vals['html'] = self.Wiki2Html(vals['text_area']) - else: - vals['text_area'] = 'Your text goes here' - vals['html'] = 'You have not create the page.' if not vals.has_key('minor_edit'): return super(Wiki,self).create(cr, uid, vals, context) - vals['history_id']=[[0,0,{'minor_edit':vals['minor_edit'],'text_area':vals['text_area'],'modify_by':uid,'summary':vals['summary']}]] + vals['history_id']=[[0,0,{'minor_edit':vals['minor_edit'],'text_area':vals['text_area'],'summary':vals['summary']}]] return super(Wiki,self).create(cr, uid, vals, context) def write(self, cr, uid, ids, vals, context=None): - vals['wiki_write_date']=time.strftime('%Y-%m-%d %H:%M:%S') - vals['last_modify_by']=uid - wiki_data=self.read(cr,uid,ids,['minor_edit','summary'])[0] +# wiki_data=self.read(cr,uid,ids,['minor_edit','summary'])[0] if vals.get('text_area'): - vals['html'] = self.Wiki2Html(vals['text_area']) +# vals['html'] = self.Wiki2Html(vals['text_area']) if vals.has_key('minor_edit') and vals.has_key('summary'): vals['history_id']=[[0,0,{'minor_edit':vals['minor_edit'],'text_area':vals['text_area'],'modify_by':uid,'summary':vals['summary']}]] elif vals.has_key('minor_edit'): @@ -144,35 +96,8 @@ class Wiki(osv.osv): return super(Wiki,self).write(cr, uid, ids, vals, context) Wiki() -#class Forum(osv.osv): -# _name="base.wiki.forum" -# _description="Wiki Forum" -# _rec_name="title" -# _columns={ -# 'title':fields.char('Title',size=128), -# 'replies':fields.integer('Replies'), -# 'wiki_authour':fields.many2one('res.users','Created By'), -# 'last_post':fields.datetime("Last Post",readonly=True), -# 'by':fields.many2one('res.users','By',readonly=True), -# 'discussion_lines':fields.one2many('base.wiki.discussion','forum_id','Discussion Lines'), -# 'wiki_id':fields.many2one('base.wiki','Wiki Id') -# } -#Forum() -# -#class Discussion(osv.osv): -# _name="base.wiki.discussion" -# _description="Wiki Discussion" -# _rec_name="wiki_authour" -# _columns={ -# 'wiki_authour':fields.many2one('res.users','Authour',readonly=True), -# 'posted_date':fields.datetime("Posted Date",readonly=True), -# 'message':fields.text('Message'), -# 'forum_id':fields.many2one('base.wiki.forum','Forum Id') -# } -#Discussion() - class History(osv.osv): - _name="base.wiki.history" + _name="wiki.wiki.history" _description="Wiki History" _rec_name="date_time" _order = 'id DESC' @@ -183,7 +108,7 @@ class History(osv.osv): 'summary':fields.char('Summary',size=256, select=True), 'modify_by':fields.many2one('res.users',"Modify By", select=True), 'hist_write_date':fields.datetime("Last modified", select=True), - 'history_wiki_id':fields.many2one('base.wiki','Wiki Id', select=True) + 'history_wiki_id':fields.many2one('wiki.wiki','Wiki Id', select=True) } _defaults = { 'hist_write_date': lambda *a: time.strftime('%Y-%m-%d %H:%M:%S'), @@ -193,7 +118,7 @@ class History(osv.osv): def getDiff(self, cr, uid, v1, v2, context={}): import difflib - history_pool = self.pool.get('base.wiki.history') + history_pool = self.pool.get('wiki.wiki.history') text1 = history_pool.read(cr, uid, [v1], ['text_area'])[0]['text_area'] text2 = history_pool.read(cr, uid, [v2], ['text_area'])[0]['text_area'] @@ -211,7 +136,7 @@ from StringIO import StringIO from HTMLParser import HTMLParser class IndexLine(osv.osv): - _name="base.index.line" + _name="wiki.index.line" _description="Index Lines" _columns={ 'name':fields.text('Content', select=True), @@ -238,15 +163,13 @@ class IndexLine(osv.osv): def Index(self, cr, uid, ids, context={}): - entry_pool = self.pool.get('base.index.line') + entry_pool = self.pool.get('wiki.index.line') eids = entry_pool.search(cr, uid, []) -# entry_pool.unlink(cr, uid, eids) -# cr.commit() model_pool = self.pool.get('ir.model') field_pool = self.pool.get('ir.model.fields') - ids = model_pool.search(cr, uid, [('model','!=','base.index.line')]) + ids = model_pool.search(cr, uid, [('model','!=','wiki.index.line')]) models = model_pool.read(cr, uid, ids, ['id', 'model']) for mod in models: @@ -258,13 +181,13 @@ class IndexLine(osv.osv): if str(mod['model']).startswith('ir'): continue - if str(mod['model']).startswith('base.index.line'): + if str(mod['model']).startswith('wiki.index.line'): continue if str(mod['model']).startswith('res.currency'): continue - if str(mod['model']).startswith('base.wiki'): + if str(mod['model']).startswith('wiki.wiki'): continue if str(mod['model']).startswith('report'): @@ -281,12 +204,6 @@ class IndexLine(osv.osv): fdata = field_pool.read(cr, uid, fids, ['name','relation', 'ttype']) except Exception, e: continue -# -# fkeys = {} -# tkeys = {} -# for fd in fdata: -# fkeys[fd['name']] = fd['relation'] -# tkeys[fd['name']] = fd['ttype'] res_pool = None res_ids = None @@ -298,8 +215,6 @@ class IndexLine(osv.osv): try: res_ids = res_pool.search(cr, 1, []) res_datas = res_pool.read(cr, 1, res_ids) - #cr.execute("select * from %s" % ( mod['model'].replace('.','_'))) - #res_datas = cr.dictfetchall() except Exception, e: print e continue @@ -314,22 +229,6 @@ class IndexLine(osv.osv): continue final_res = '' -# -# for col in res_data: -# if fkeys.has_key(col) and fkeys[col] != 'NULL': -# if tkeys.has_key(col) and tkeys[col] == 'one2many': -# rel_pool = self.pool.get(fkeys.get(col)) -# try: -# foreign_key = res_pool._columns[col]._fields_id -# except Exception, e: -# print e -# continue -# fkids = rel_pool.search(cr, 1, [(foreign_key, '=', res_data['id'])]) -# if fkids.__len__() > 0: -# fkdata = rel_pool.read(cr, 1, fkids) -# for fkd in fkdata: -# final_res += ' '.join(map(str,fkd.values())) - final_res += ' '.join(map(str,res_data.values())) entry_pool.create(cr, uid, { @@ -346,12 +245,8 @@ class IndexLine(osv.osv): def getResult(self, cr, uid, key, reSearch=True, context = {}): -# password = self.pool.get('res.users').browse(cr, uid, uid).password -# self.server.init(cr.dbname, uid, password, True) - if context and context.get('read_all') and key: try: - #res = self.server.search(key) ids = self.search(cr, uid, [('name','ilike',key)]) res = self.read(cr, uid, ids, ['model', 'res_id']) except Exception, e: @@ -399,25 +294,11 @@ class IndexLine(osv.osv): sbuff = '\n==' + mod_data + '==\n' + sbuff buffer += sbuff - html = self.pool.get('base.wiki').Wiki2Html(buffer) + html = self.pool.get('wiki.wiki').Wiki2Html(buffer) html = html.replace('$s', '') html = html.replace('$es', '') return [{'html':html}] -# else: -# #TODO: need to create an index on the new records -# if reSearch: -# self.Index(cr, uid, context) -# self.getResult(cr, uid, key, False, context) return None -IndexLine() - -class Project(osv.osv): - _inherit = 'project.project' - _name = 'project.project' - _columns = { - 'wiki':fields.many2one('base.wiki', 'Wiki'), - 'dwiki':fields.many2one('base.wiki', 'Developer Wiki'), - } -Project() +IndexLine() \ No newline at end of file diff --git a/addons/wiki/wiki_data.xml b/addons/wiki/wiki_data.xml index 447dcf374f2..74d90b8614c 100755 --- a/addons/wiki/wiki_data.xml +++ b/addons/wiki/wiki_data.xml @@ -1,12 +1,119 @@ - - - Wiki Home - home + + + Wiki Home False + + +Often used for discussion on talk pages. +: We use 1 colon to indent once. +:: We use 2 colons to indent twice. +::: 3 colons to indent 3 times, and so on. +==Formatting Test - 7== +Here's a link to the [[ Main page ]]. +==Formatting Test - 8== +[[Intentionally permanent red link]] is +a page that doesn't exist +yet. You could create it by +clicking on the link. +==Formatting Test - 9== +You can link to a page section by its title: +* [[Help:Contents#For editors]]. +If multiple sections have the same title, add +a number. [[#Example section 3]] goes to the +third section named "Example section". +==Formatting Test-10== +Here's a ''definition list'': +; Word : Definition of the word +; A longer phrase needing definition +: Phrase defined +; A word : Which has a definition +: Also a second one +: And even a third + +Begin with a semicolon. One item per line; +a newline can appear before the colon, but +using a space before the colon improves +parsing. +==Formatting Test - 11== +You can add footnotes to sentences using +the ''ref'' tag -- this is especially good +for citing a source. + +:There are over six billion people in the +world.CIA World Factbook, 2006. + +For details, see [[Footnotes | Wikipedia:Footnotes]] +and [[Help:Footnotes]]. +==Formatting Test - 12== +This is a Link +[[Page | MainPage]] do not show up in line +but instead at page bottom +''and cause the page to be listed in the category.'' +[[Category:English documentation]] + +Add an extra colon to ''link'' to a category in line +without causing the page to be listed in the category: +[[:Category:English documentation]] +==Formatting Test-12== +===Apple Desktop Image=== +img://apple.jpg +===Ubuntu Desktop Image=== +img://ubuntu-01.jpg]]> - \ No newline at end of file diff --git a/addons/wiki/wiki_view.xml b/addons/wiki/wiki_view.xml index 43299fedcaa..c135e7427f7 100755 --- a/addons/wiki/wiki_view.xml +++ b/addons/wiki/wiki_view.xml @@ -2,41 +2,36 @@ - base.wiki.tree - base.wiki + wiki.wiki.tree + wiki.wiki tree - - - - + + + - base.wiki.form - base.wiki + wiki.wiki.form + wiki.wiki form
    - + + + + - - - - - - - - - - - - + + + + + @@ -59,33 +54,17 @@ Wiki Pages - base.wiki + wiki.wiki form form,tree - - - - - base.wiki.forum.tree - base.wiki.forum - tree - - - - - - - - - - + - base.wiki.history.tree - base.wiki.history + wiki.wiki.history.tree + wiki.wiki.history tree @@ -98,8 +77,8 @@ - base.wiki.history.form - base.wiki.history + wiki.wiki.history.form + wiki.wiki.history form @@ -114,7 +93,7 @@ Wiki History - base.wiki.history + wiki.wiki.history form form,tree @@ -122,44 +101,9 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - base.index.line.form - base.index.line + wiki.index.line.form + wiki.index.line form @@ -173,8 +117,8 @@ - base.index.line.tree - base.index.line + wiki.index.line.tree + wiki.index.line form @@ -186,64 +130,13 @@ Index Server - base.index.line + wiki.index.line form tree,form - + - - - - - project.project.form - project.project - - form - - - - - - - - - - - \ No newline at end of file