Description: Web pretreatment program, to convert web pages into text form, you can debug the program
To Search:
File list (Check if you may need any files):
Preprocess
..........\.classpath
..........\.project
..........\bin
..........\...\cn
..........\...\..\edu
..........\...\..\...\bjfu
..........\...\..\...\....\search
..........\...\..\...\....\......\extractor
..........\...\..\...\....\......\.........\Extractor.class
..........\...\..\...\....\......\index
..........\...\..\...\....\......\.....\IndexBuilder.class
..........\...\..\...\....\......\page
..........\...\..\...\....\......\....\Page.class
..........\...\..\...\....\......\....\PageLib.class
..........\...\..\...\....\......\util
..........\...\..\...\....\......\....\CharacterHandle.class
..........\...\..\...\....\......\....\MD5.class
..........\...\..\...\....\......\....\ProperConfig.class
..........\...\..\...\....\......\....\Query.class
..........\...\..\...\....\......\....\TestExtractor.class
..........\...\..\...\....\......\....\TestIndexer.class
..........\...\config.properties
..........\files
..........\.....\0003439af05199754cf0ab56bcfee4db
..........\.....\000c93922ad8a92b3ba1cdebcc59f486
..........\.....\00221be01f6f27ce237026a67e57e46c
..........\.....\0054222570d487779a2cc77c557b098b
..........\.....\0099ce4b609548c32a3144e2593b6f7c
..........\.....\00a847afd8ee3cb9ac4edc524db529b4
..........\.....\00c60689527c7a1350b33870c1b2ea75
..........\.....\0136279422854250cde0b3246a270d0f
..........\.....\01d6bafd709eb4989494c7d1e810a72c
..........\.....\01f023905675899fee173f928b365389
..........\.....\02fae58e06550a39e44e814ffb6daff9
..........\.....\03179b85f1d083ea4b577456d3e024be
..........\.....\033a0c76cac327b14409067c31c56273
..........\.....\033b6fa73ec34be3abfa3761233206e0
..........\.....\0379ab236216dd951f64702fa16cc4e6
..........\.....\0381493b45fc7c678c83e3beaaccd346
..........\.....\03887222087f87721e99e49620eed454
..........\.....\03a24ad09aef3d6f4718b0fc76b297e5
..........\.....\03cf1e4a8e809ec63db14c957b697cb1
..........\.....\040e351eb38c934a4140a38767f1ce24
..........\.....\04e23bd5560fd6261c2203be188388db
..........\.....\04edeed34812cf441373518d73c813bd
..........\.....\04f2566638dabe2ebf6e0c90a5081c1d
..........\.....\0520fb90f196eb8e6f7feeac9bbcc2c2
..........\.....\05263a903ae4e9255471ccdc553f6639
..........\.....\05a409df797fa46420ba10b8c974b8a5
..........\.....\05e15b0861b335a7ed83fbdcc8cecf79
..........\.....\05e985c9d92dae5d3ec5eab56a2aef05
..........\.....\05fbaec25b9e245eaa67b08451f93923
..........\.....\0607d2e609119ad1038433f71ef1f0f2
..........\.....\06596053307267b6cee8c3b0c619d22d
..........\.....\06a49b8a3dea1bd0373ee1a9898cd1a9
..........\.....\06f6bee83e620eb1d631ce94b14f74d5
..........\.....\07234dd15764fd815caae0c386b1fa60
..........\.....\078a01a1cc30b611d2cfc2b25bb3806c
..........\.....\07a4f835e24b3aa196712bb26fa4ca29
..........\.....\07b88fe5f6b79d9b58611036c7cf1d86
..........\.....\0804d88c25a1b796954e236ebc1e5702
..........\.....\08a0840d4dcbbb12f2dce4b318aabf48
..........\.....\08b79e224aae9195691ad36c780985ed
..........\.....\08e29d561945f5d2b1bd97b0fbab0305
..........\.....\090f3614c54270ee91b02de27b6b0966
..........\.....\090fb752ae19d48c4c9fe4b081c5463c
..........\.....\094083fc7b65890450c3859bca592761
..........\.....\0951961cfb0315a7f3d16c6d292715b3
..........\.....\0973eba6949750a438c549b045a63688
..........\.....\0984eef2946c66f55bb867d849f9b17a
..........\.....\099ebe5a94a3854d06908c65b099ebe3
..........\.....\0aa656f38e1f53009915530435167e00
..........\.....\0ab865131dc09fb26ae1efe4a9aa370b
..........\.....\0ad1e6969c7a834eaa6d850126aed3f7
..........\.....\0b1966e8ec0546183021bd5cd368a1d5
..........\.....\0b33d0dacbffccb008bf8d6538386088
..........\.....\0ba88f7506b897532907a6e7f00be6f7
..........\.....\0bc0e91b12320f2e5adb2b34b72ac0b9
..........\.....\0c062ae096c9ed17b303bd05aa4cf58c
..........\.....\0c61f385413c04b465f2acd07400e743
..........\.....\0cb41f77f732fa216331eb3cf3c3d097
..........\.....\0cc5eb7ddf5a566ab03352011e035f75
..........\.....\0d2565344139cca23d160d61ba91fc3c
..........\.....\0d5901f73cc0b6c8c0107321689d3e5e
..........\.....\0d610de5db86c79056f6c4cde318b846
..........\.....\0d73a123d009ba89c4886c4ef7b9ea22
....