lib/nlp/examples/nlp_index.nit

   1 # This file is part of NIT ( http://www.nitlanguage.org ).
   2 #
   3 # Licensed under the Apache License, Version 2.0 (the "License");
   4 # you may not use this file except in compliance with the License.
   5 # You may obtain a copy of the License at
   6 #
   7 #     http://www.apache.org/licenses/LICENSE-2.0
   8 #
   9 # Unless required by applicable law or agreed to in writing, software
  10 # distributed under the License is distributed on an "AS IS" BASIS,
  11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12 # See the License for the specific language governing permissions and
  13 # limitations under the License.
  14
  15 # Example showing how to use a NLPFileIndex.
  16 module nlp_index
  17
  18 import nlp
  19 import config
  20
  21 redef class Config
  22
  23         # --whitelist-exts
  24         var opt_white_exts = new OptionArray("Allowed file extensions (default is [])",
  25                 "-w", "--whitelist-exts")
  26
  27         # --blacklist-exts
  28         var opt_black_exts = new OptionArray("Allowed file extensions (default is [])",
  29                 "-b", "--blacklist-exts")
  30
  31         # --server
  32         var opt_server = new OptionString("StanfordNLP server URI (default is https://localhost:9000)",
  33                 "-s", "--server")
  34
  35         # --lang
  36         var opt_lang = new OptionString("Language to use (default is fr)", "-l", "--lang")
  37
  38         redef init do
  39                 opts.add_option(opt_server, opt_lang, opt_white_exts, opt_black_exts)
  40         end
  41 end
  42
  43 var config = new Config
  44 config.tool_description = "usage: example_index <files>"
  45 config.parse_options(args)
  46
  47 if args.length < 1 then
  48         config.usage
  49         exit 1
  50 end
  51
  52 var host = config.opt_server.value
  53 if host == null then host = "http://localhost:9000"
  54 var lang = config.opt_lang.value
  55 if lang == null then lang = "en"
  56
  57 var cli = new NLPClient(host)
  58 cli.language = lang
  59
  60 var bl = config.opt_black_exts.value
  61 if bl.is_empty then bl = ["CD", "SYM", "-RRB-", "-LRB-", "''", "``", ".", "#", ":", ",", "$", ""]
  62
  63 var index = new NLPFileIndex(cli)
  64 index.whitelist_exts = config.opt_white_exts.value
  65 index.blacklist_exts = bl
  66
  67 print "Building index..."
  68 index.index_files(args, true)
  69
  70 print "Indexed {index.documents.length} documents"
  71
  72 loop
  73         print "\nEnter query:"
  74         printn "> "
  75         var input = sys.stdin.read_line
  76         var matches = index.match_string(input)
  77
  78         for match in matches do
  79                 print match
  80         end
  81 end