#!/usr/bin/python # -*- coding: iso-8859-1 -*- # # LanguageTool -- A Rule-Based Style and Grammar Checker # Copyright (C) 2002,2003,2004 Daniel Naber # # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library 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 # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the Free Software # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA import cgi import string import sys import os os.chdir(sys.path[0]) sys.path.append(sys.path[0]) sys.path.append(os.path.join(sys.path[0], "src")) import TagInfo import TextChecker # FIXME: for debugging only import cgitb cgitb.enable() def main(): form = cgi.FieldStorage() if form.getvalue("text"): check(form) elif form.getvalue("explain"): displayExplanation(form) else: displayForm(form) return def displayExplanation(form): print "Content-Type: text/html\n\n" tag = cgi.escape(form.getvalue("explain")) # security: anti XSS taginfo = TagInfo.TagInfo(form.getvalue("lang")) print """ LanguageTool: Tag explanation for %s

Tag explanation for %s

%s: %s

""" % (tag, tag, tag, taginfo.getExp(form.getvalue("explain"))) return def displayForm(form): print "Content-Type: text/html\n\n" print """ LanguageTool Web Interface

LanguageTool Web Interface

Enter text here:

Suggested test text
The incorrect words are red (copy and paste into text field to try it):

Then he look at the building.
I definitely think is should be less than four years.
This allows to provide a powerful a help system.
His house is as big like mine.
His car is larger then mine.

LanguageTool Homepage """ return def check(form): print "Content-Type: text/html\n\n" text = form.getvalue("text").decode('latin1') if not text: text = "" # TODO: put options for alle these in the web page? too confusing... grammar = None falsefriends = None words = None builtin = None textlanguage = "en" if not form.getvalue("style"): words = ["__NONE"] mothertongue = "de" if not form.getvalue("german_ff"): mothertongue = None if form.getvalue("lang"): textlanguage = form.getvalue("lang") max_sentence_length = 0 if form.getvalue("sentencelength"): max_sentence_length = None checker = TextChecker.TextChecker(grammar, falsefriends, words, builtin, \ textlanguage, mothertongue, max_sentence_length) print """ Check result

Result

""" (rule_matches, res, tags) = checker.check(text) # TODO: add an option to print the complete checker XML response: #print "XML reply:

%s

" % cgi.escape(res) #print "

%s

" % tags taglist = [] char_count = 0 list_count = 0 text_list = [] for tag_triple in tags: tag_str = "" if form.getvalue("tags") and tag_triple[2]: w = tag_triple[2] tag_str = '[%s]' \ % (w, textlanguage, w, w) if tag_triple[2] == 'SENT_END': tag_str = '%s
\n' % tag_str word = cgi.escape(tag_triple[0]) text_list.append(word) text_list.append(tag_str) char_count = char_count + len(word) # guarantee that the rule_matches are ordered by their position: rule_matches.sort() rule_matches.reverse() # add messages from end of list to avoid count confusion for rule_match in rule_matches: # TODO: this produces invalid code if the rule ranges are nested! ct = 0 i = 0 start_found = 0 end_found = 0 for el in text_list: if not el.startswith("= from_pos and not end_found: text_list[i] = '%s[%s (%s)]' % (text_list[i], \ rule_match.message, rule_match.id) end_found = 1 elif rule_match.from_pos <= to_pos and rule_match.from_pos >= from_pos and not start_found: text_list[i] = '%s' % text_list[i] start_found = 1 ct = ct + len(el) if end_found and start_found: break i = i + 1 text = string.join(text_list, '') print text.encode('latin1') if len(rule_matches) == 1: print "