| Index: trunk/lucene-search-3/src/main/webapp/webinterface/lsweb.py |
| — | — | @@ -0,0 +1,496 @@ |
| | 2 | +import string,cgi,time,urlparse,urllib2, urllib, cgi, copy |
| | 3 | +import re, time, math |
| | 4 | +from htmlentitydefs import name2codepoint |
| | 5 | +from os import curdir, sep |
| | 6 | +from BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer |
| | 7 | +from urllib2 import URLError, HTTPError |
| | 8 | + |
| | 9 | +#search_host = { 'enwiki' : "srv79:8123", '<default>': 'srv79:8123' } |
| | 10 | +search_host = {'<default>' : 'srv79:8123', |
| | 11 | + 'jawiki' : "localhost:8123", |
| | 12 | + 'frwiki' : "localhost:8123", |
| | 13 | + 'dewiki' : "localhost:8123", |
| | 14 | + 'itwiki' : "localhost:8123", |
| | 15 | + 'jawikiquote' : "localhost:8123", |
| | 16 | + 'wikilucene' : 'localhost:8123' } |
| | 17 | +#search_host = {'<default>' : 'localhost:8123'} |
| | 18 | + |
| | 19 | +canon_namespaces = { 0 : '', 1: 'Talk', 2: 'User', 3: 'User_talk', |
| | 20 | + 4 : 'Project', 5 : 'Project_talk', 6 : 'Image', 7 : 'Image_talk', |
| | 21 | + 8 : 'MediaWiki', 9: 'MediaWiki_talk', 10: 'Template', 11: 'Template_talk', |
| | 22 | + 12 : 'Help', 13: 'Help_talk', 14: 'Category', 15: 'Category_talk', |
| | 23 | + 100: 'Portal', 101: 'Portal_talk', 102: 'Extension', 103: 'Extension_talk', |
| | 24 | + 104: 'Index', 105:' Index_talk', 112: 'Portal', 113: 'Portal_talk'} |
| | 25 | +prefix_aliases = { 'm': 0, 'mt' : 1, 'u' : 2, 'ut' : 3, 'p': 4, 'pt':5, 'i':6, 'it':7, |
| | 26 | + 'mw':8, 'mwt':9, 't':10, 'tt':11, 'h':12, 'ht':13, 'c':14, 'ct': 15} |
| | 27 | + |
| | 28 | +snippet_separator = " <b>...</b> "; |
| | 29 | + |
| | 30 | +def make_link(params,offset,method='search',query=None): |
| | 31 | + ''' Duplicate existing query (denoted by params), but with a different offset ''' |
| | 32 | + dupl = copy.copy(params) |
| | 33 | + dupl['offset'] = [offset] |
| | 34 | + if query != None: |
| | 35 | + dupl['query'] = [query] |
| | 36 | + return '/%s?%s' % (method,urllib.urlencode(dupl,True)) |
| | 37 | + |
| | 38 | + |
| | 39 | +def rewrite_callback(match): |
| | 40 | + namespaces = [] |
| | 41 | + for prefix in match.group(1).split(','): |
| | 42 | + # check for canonical namespace names |
| | 43 | + iscanonical = False |
| | 44 | + for ns,name in canon_namespaces.iteritems(): |
| | 45 | + if name.lower() == prefix.lower(): |
| | 46 | + iscanonical = True # is there a way to continue outer loop in python? |
| | 47 | + namespaces.append(str(ns)) |
| | 48 | + break |
| | 49 | + if iscanonical: |
| | 50 | + continue |
| | 51 | + # check aliases |
| | 52 | + if prefix_aliases.has_key(prefix): |
| | 53 | + namespaces.append(str(prefix_aliases[prefix])) |
| | 54 | + continue |
| | 55 | + |
| | 56 | + if namespaces!=[]: |
| | 57 | + return '[%s]:' % ','.join(namespaces) |
| | 58 | + else: |
| | 59 | + return match.group() |
| | 60 | + |
| | 61 | + |
| | 62 | +def rewrite_query(query): |
| | 63 | + '''Rewrite query prefixes, port of php version in LuceneSearch extension''' |
| | 64 | + query = query.decode('utf-8') |
| | 65 | + prefix_re = re.compile('([a-zA-Z0-9_,]+):') # we will parse only canonical namespaces here |
| | 66 | + |
| | 67 | + return prefix_re.sub(rewrite_callback,query) |
| | 68 | + |
| | 69 | +def make_wiki_link(line,dbname,caption=''): |
| | 70 | + parts = line.split(' ') |
| | 71 | + score = float(parts[0]) |
| | 72 | + title = '' |
| | 73 | + if len(parts) == 3: |
| | 74 | + ns = canon_namespaces[int(parts[1])] |
| | 75 | + if ns != '': |
| | 76 | + ns = ns +":" |
| | 77 | + title = ns+parts[2] |
| | 78 | + else: |
| | 79 | + iw = parts[1] |
| | 80 | + ns = canon_namespaces[int(parts[2])] |
| | 81 | + if ns != '': |
| | 82 | + ns = ns +":" |
| | 83 | + title = iw+':'+ns+parts[3] |
| | 84 | + |
| | 85 | + if dbname == 'mediawikiwiki': |
| | 86 | + link= 'http://www.mediawiki.org/wiki/%s' % (title) |
| | 87 | + elif dbname == 'metawiki': |
| | 88 | + link = 'http://meta.wikimedia.org/wiki/%s' % (title) |
| | 89 | + elif dbname.endswith('wiktionary'): |
| | 90 | + link = 'http://%s.wiktionary.org/wiki/%s' % (dbname[0:2],title) |
| | 91 | + else: |
| | 92 | + link = 'http://%s.wikipedia.org/wiki/%s' % (dbname[0:2],title) |
| | 93 | + decoded = urllib.unquote(title.replace('_',' ')) |
| | 94 | + if caption !='': |
| | 95 | + caption = ns+urllib.unquote(caption.replace('_',' ')) |
| | 96 | + else: |
| | 97 | + caption = decoded |
| | 98 | + return ['%1.2f -- <a href="%s">%s</a>' % (score,link,caption),title] |
| | 99 | + |
| | 100 | +def make_title_link(line,dbname,caption=''): |
| | 101 | + interwiki={'w':'wikipedia', 'wikt':'wiktionary', 's':'wikisource', 'b': 'wikibooks', 'n':'wikinews', 'v':'wikiversity', 'q':'wikiquote', |
| | 102 | + 'mw': 'mediawiki', 'meta': 'meta', 'wikinews': 'wikinews'}; |
| | 103 | + parts = line.split(' ') |
| | 104 | + score = float(parts[0]) |
| | 105 | + title = '' |
| | 106 | + iw = parts[1] |
| | 107 | + # ns = canon_namespaces[int(parts[2])] |
| | 108 | + ns = urllib.unquote(parts[3]) |
| | 109 | + if ns != '': |
| | 110 | + ns = ns +":" |
| | 111 | + title = iw+':'+ns+parts[4] |
| | 112 | + titleText = ns+parts[4] |
| | 113 | + |
| | 114 | + if dbname == 'mediawikiwiki': |
| | 115 | + link= 'http://www.mediawiki.org/wiki/%s' % (title) |
| | 116 | + elif dbname == 'metawiki': |
| | 117 | + link = 'http://meta.wikimedia.org/wiki/%s' % (title) |
| | 118 | + elif dbname.endswith('wiktionary'): |
| | 119 | + link = 'http://%s.wiktionary.org/wiki/%s' % (dbname[0:2],title) |
| | 120 | + else: |
| | 121 | + link = 'http://%s.wikipedia.org/wiki/%s' % (dbname[0:2],title) |
| | 122 | + decoded = urllib.unquote(titleText.replace('_',' ')) |
| | 123 | + if caption!='': |
| | 124 | + caption = ns+urllib.unquote(caption.replace('_',' ')) |
| | 125 | + else: |
| | 126 | + caption = decoded |
| | 127 | + return ['%s : (%1.2f) <a href="%s">%s</a>' % (interwiki[iw],score,link,caption),title] |
| | 128 | + |
| | 129 | +def extract_snippet(line,final_separator=True,originalIsKey=False): |
| | 130 | + parts = line.split(' ') |
| | 131 | + type = parts[0] |
| | 132 | + splits = de_bracket_split(parts[1]) |
| | 133 | + highlight = de_bracket_split(parts[2]) |
| | 134 | + suffix = urllib.unquote_plus(de_bracket(parts[3])) |
| | 135 | + text = urllib.unquote_plus(parts[4].strip()) |
| | 136 | + original = None |
| | 137 | + if len(parts) > 5: |
| | 138 | + original = urllib.unquote_plus(parts[5].strip()) |
| | 139 | + |
| | 140 | + splits.append(len(text)) |
| | 141 | + start = 0 |
| | 142 | + snippet = "" |
| | 143 | + hi = 0 |
| | 144 | + for sp in splits: |
| | 145 | + sp = int(sp) |
| | 146 | + while hi < len(highlight) and int(highlight[hi]) < sp: |
| | 147 | + s = int(highlight[hi]) |
| | 148 | + e = int(highlight[hi+1]) |
| | 149 | + snippet += text[start:s] + "<b>" + text[s:e] + "</b>" |
| | 150 | + start = e |
| | 151 | + hi += 2 |
| | 152 | + snippet += text[start:sp] |
| | 153 | + if sp == len(text) and suffix != '': |
| | 154 | + snippet += suffix |
| | 155 | + elif final_separator: |
| | 156 | + snippet += snippet_separator |
| | 157 | + start = sp; |
| | 158 | + if originalIsKey: |
| | 159 | + origParts = original.split(":") |
| | 160 | + origNs = canon_namespaces[int(origParts[0])] |
| | 161 | + if origNs != '': |
| | 162 | + origNs = origNs +":" |
| | 163 | + original = origNs+origParts[1] |
| | 164 | + snippet = origNs+snippet; |
| | 165 | + |
| | 166 | + return [snippet,original] |
| | 167 | + |
| | 168 | +def extract_suggest(line): |
| | 169 | + parts = line.split(' ') |
| | 170 | + type = parts[0] |
| | 171 | + highlight = de_bracket_split(parts[1]) |
| | 172 | + text = urllib.unquote_plus(parts[2].strip()) |
| | 173 | + |
| | 174 | + start = 0 |
| | 175 | + snippet = "" |
| | 176 | + hi = 0 |
| | 177 | + while hi < len(highlight): |
| | 178 | + s = int(highlight[hi]) |
| | 179 | + e = int(highlight[hi+1]) |
| | 180 | + snippet += text[start:s] + "<i>" + text[s:e] + "</i>" |
| | 181 | + start = e |
| | 182 | + hi += 2 |
| | 183 | + if start < len(text): |
| | 184 | + snippet += text[start:len(text)] |
| | 185 | + |
| | 186 | + for key,val in canon_namespaces.iteritems(): |
| | 187 | + snippet = snippet.replace('[%d]' % key, val) |
| | 188 | + |
| | 189 | + return [snippet,text] |
| | 190 | + |
| | 191 | + |
| | 192 | +def de_bracket(s): |
| | 193 | + return s[1:len(s)-1] |
| | 194 | + |
| | 195 | +def de_bracket_split(s): |
| | 196 | + if s == '[]': |
| | 197 | + return [] |
| | 198 | + else: |
| | 199 | + return de_bracket(s).split(',') |
| | 200 | + |
| | 201 | +class MyHandler(BaseHTTPRequestHandler): |
| | 202 | + def do_GET(self): |
| | 203 | + try: |
| | 204 | + s = urlparse.urlparse(self.path) |
| | 205 | + if s[2] == '/search' or s[2] == '/related': |
| | 206 | + method = s[2][1:] |
| | 207 | + start_time = time.time() |
| | 208 | + params = {} |
| | 209 | + # parse key1=val1&key2=val2 syntax |
| | 210 | + params = cgi.parse_qs(s[4]) |
| | 211 | + |
| | 212 | + # defaults |
| | 213 | + limit = 20 |
| | 214 | + offset = 0 |
| | 215 | + namespaces = [] |
| | 216 | + case = "ignore" |
| | 217 | + |
| | 218 | + # parameters |
| | 219 | + for key,val in params.iteritems(): |
| | 220 | + if key == 'dbname': |
| | 221 | + dbname = val[0] |
| | 222 | + elif key == 'query': |
| | 223 | + query = val[0] |
| | 224 | + elif key == 'limit': |
| | 225 | + limit = int(val[0]) |
| | 226 | + elif key == 'offset': |
| | 227 | + offset = int(val[0]) |
| | 228 | + elif key.startswith('ns'): |
| | 229 | + namespaces.append(key[2:]) |
| | 230 | + |
| | 231 | + rewritten = rewrite_query(query) |
| | 232 | + |
| | 233 | + if search_host.has_key(dbname): |
| | 234 | + host = search_host[dbname] |
| | 235 | + else: |
| | 236 | + host = search_host['<default>'] |
| | 237 | + |
| | 238 | + if dbname.endswith("-exact"): |
| | 239 | + case = "exact" |
| | 240 | + dbname = dbname[0:-6] |
| | 241 | + |
| | 242 | + # make search url for ls2 |
| | 243 | + search_url = 'http://%s/%s/%s/%s' % (host,method,dbname,urllib.quote(rewritten.encode('utf-8'))) |
| | 244 | + search_params = urllib.urlencode({'limit' : limit, 'offset' : offset, 'namespaces' : ','.join(namespaces), "case" : case}, True) |
| | 245 | + |
| | 246 | + # process search results |
| | 247 | + try: |
| | 248 | + results = urllib2.urlopen(search_url+"?"+search_params) |
| | 249 | + numhits = int(results.readline()) |
| | 250 | + lasthit = min(offset+limit,numhits) |
| | 251 | + # info |
| | 252 | + infoLine = results.readline() |
| | 253 | + # suggestions |
| | 254 | + suggest = results.readline() |
| | 255 | + suggestHl = "" |
| | 256 | + if suggest.startswith("#suggest "): |
| | 257 | + [suggestHl,suggest] = extract_suggest(suggest) |
| | 258 | + else: |
| | 259 | + suggest = "" |
| | 260 | + # interwiki |
| | 261 | + interwiki_count = results.readline(); |
| | 262 | + interwiki_count = int(interwiki_count.split(' ')[1]) |
| | 263 | + i = 0 |
| | 264 | + interwiki = [] |
| | 265 | + line = results.readline() |
| | 266 | + nextLine = '' |
| | 267 | + while not line.startswith("#results"): |
| | 268 | + if not line.startswith('#'): |
| | 269 | + titleHl = '' |
| | 270 | + redirectHl = '' |
| | 271 | + redirectLink = None |
| | 272 | + nextLine = results.readline() |
| | 273 | + if nextLine.startswith('#h.title'): |
| | 274 | + [titleHl, orig] = extract_snippet(nextLine,False) |
| | 275 | + nextLine = results.readline() |
| | 276 | + if nextLine.startswith('#h.redirect'): |
| | 277 | + [redirectHl, redirectLink] = extract_snippet(nextLine,False); |
| | 278 | + if redirectLink != None: |
| | 279 | + redirectLink = 'http://%s.wikipedia.org/wiki/%s' % (dbname[0:2],redirectLink) |
| | 280 | + elif nextLine.startswith('#h.redirect'): |
| | 281 | + [redirectHl, redirectLink] = extract_snippet(nextLine,False); |
| | 282 | + if redirectLink != None: |
| | 283 | + redirectLink = 'http://%s.wikipedia.org/wiki/%s' % (dbname[0:2],redirectLink) |
| | 284 | + |
| | 285 | + interwikiHtml = make_title_link(line,dbname,titleHl)[0] |
| | 286 | + if redirectLink != None: |
| | 287 | + interwikiHtml += '<small> (redirect <a href="%s">%s</a>)</small>' % (redirectLink.strip(), redirectHl) |
| | 288 | + interwiki.append(interwikiHtml) |
| | 289 | + |
| | 290 | + if nextLine == '': |
| | 291 | + line = results.readline() |
| | 292 | + else: |
| | 293 | + line = nextLine |
| | 294 | + nextLine = '' |
| | 295 | + if line.startswith('#h.date'): |
| | 296 | + line = results.readline() # just skip |
| | 297 | + if line.startswith('#h.wordcount'): |
| | 298 | + line = results.readline() # just skip |
| | 299 | + |
| | 300 | + # html headers |
| | 301 | + self.send_response(200) |
| | 302 | + self.send_header('Cache-Control','no-cache') |
| | 303 | + self.send_header('Content-type','text/html') |
| | 304 | + self.end_headers() |
| | 305 | + self.wfile.write('<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /><title>LS2 search: %s</title></head>' % query) |
| | 306 | + if method == 'related': |
| | 307 | + self.wfile.write('<body>Articles related to article: %s <br>' % query) |
| | 308 | + else: |
| | 309 | + self.wfile.write('<body>Query: %s <br>' % query) |
| | 310 | + if suggest != "": |
| | 311 | + sparams = params.copy() |
| | 312 | + sparams['query'] = suggest; |
| | 313 | + slink = make_link(sparams,0,method) |
| | 314 | + self.wfile.write('Did you mean: <a href="%s">%s</a><br>' % (slink,suggestHl)) |
| | 315 | + |
| | 316 | + # generate next/prev searchbar |
| | 317 | + if offset != 0: |
| | 318 | + link = make_link(params,max(offset-limit,0),method) |
| | 319 | + prev = '<a href="%s">< Previous %s</a>' % (link,limit) |
| | 320 | + else: |
| | 321 | + prev = "< Previous" |
| | 322 | + if numhits > lasthit: |
| | 323 | + link = make_link(params,offset+limit,method) |
| | 324 | + next = '<a href="%s">Next %s ></a>' % (link,limit) |
| | 325 | + else: |
| | 326 | + next = "Next >" |
| | 327 | + searchbar = '<a href="https://www.mediawiki.org/">New search</a> | %s -- %s | Total results: %d' % (prev, next, numhits) |
| | 328 | + |
| | 329 | + |
| | 330 | + # show upper search bar |
| | 331 | + self.wfile.write(searchbar) |
| | 332 | + self.wfile.write('<hr>Showing results %d - %d<br>' % (offset,lasthit)) |
| | 333 | + |
| | 334 | + # begin the main results table |
| | 335 | + self.wfile.write('<table><tr><td>') |
| | 336 | + |
| | 337 | + # show results |
| | 338 | + self.wfile.write('Score / Article<br>') |
| | 339 | + lines = [] |
| | 340 | + for line in results: |
| | 341 | + lines.append(line) |
| | 342 | + i = 0 |
| | 343 | + while i < len(lines): |
| | 344 | + scoreLine = lines[i]; |
| | 345 | + # decode highlight info |
| | 346 | + textHl = '' |
| | 347 | + redirectHl = '' |
| | 348 | + redirectLink = None |
| | 349 | + sectionHl = '' |
| | 350 | + sectionLink = None |
| | 351 | + titleHl = '' |
| | 352 | + date = None; |
| | 353 | + wordcount = None; |
| | 354 | + [link,title] = make_wiki_link(scoreLine,dbname) |
| | 355 | + while i+1 < len(lines): |
| | 356 | + extra = lines[i+1] |
| | 357 | + if extra.startswith('#h.text'): |
| | 358 | + [newtext, orig] = extract_snippet(extra) |
| | 359 | + textHl += newtext |
| | 360 | + elif extra.startswith('#h.title'): |
| | 361 | + [titleHl, orig] = extract_snippet(extra,False) |
| | 362 | + [link,title] = make_wiki_link(scoreLine,dbname,titleHl) |
| | 363 | + elif extra.startswith('#h.redirect'): |
| | 364 | + [redirectHl, redirectLink] = extract_snippet(extra,False,True); |
| | 365 | + if redirectLink != None: |
| | 366 | + redirectLink = 'http://%s.wikipedia.org/wiki/%s' % (dbname[0:2],redirectLink) |
| | 367 | + elif extra.startswith('#h.section'): |
| | 368 | + [sectionHl, sectionLink] = extract_snippet(extra,False); |
| | 369 | + if sectionLink != None: |
| | 370 | + sectionLink = 'http://%s.wikipedia.org/wiki/%s#%s' % (dbname[0:2],title,sectionLink) |
| | 371 | + elif extra.startswith('#h.date'): |
| | 372 | + date = extra.split(' ')[1] |
| | 373 | + elif extra.startswith('#h.wordcount'): |
| | 374 | + wordcount = extra.split(' ')[1] |
| | 375 | + elif not extra.startswith('#h'): |
| | 376 | + break |
| | 377 | + i+=1 |
| | 378 | + |
| | 379 | + self.wfile.write(link) # title link |
| | 380 | + if redirectLink != None: |
| | 381 | + self.wfile.write('<small> (redirect <a href="%s">%s</a>)</small>' % (redirectLink.strip(), redirectHl)) |
| | 382 | + if sectionLink != None: |
| | 383 | + self.wfile.write('<small> (section <a href="%s">%s</a></small>)' % (sectionLink.strip(), sectionHl)) |
| | 384 | + self.wfile.write('<br>'); |
| | 385 | + if textHl != '': |
| | 386 | + textHl = textHl |
| | 387 | + self.wfile.write('<div style="width:500px"><font size="-1">%s</font></div>' % textHl) |
| | 388 | + if date != None: |
| | 389 | + self.wfile.write('<font size="-1"><i>Date: %s</i></font>' % date) |
| | 390 | + if wordcount != None: |
| | 391 | + dateprefix = '' |
| | 392 | + if date != None: |
| | 393 | + dateprefix = ' -- ' |
| | 394 | + self.wfile.write('<font size="-1">%s<i>%s words</i></font>' % (dateprefix,wordcount)) |
| | 395 | + if date != None or wordcount != None: |
| | 396 | + self.wfile.write(' -- ') |
| | 397 | + self.wfile.write('<font size="-1"><a href="%s">Related</a></font><br/>' % make_link(params,0,'related',urllib.unquote(title.replace('_',' ')))) |
| | 398 | + i += 1 |
| | 399 | + |
| | 400 | + # write the grouped titles stuff |
| | 401 | + self.wfile.write('</td><td width=35% valign=top>') |
| | 402 | + if interwiki != []: |
| | 403 | + self.wfile.write('From sister projects:<br/>') |
| | 404 | + self.wfile.write('<font size="-1">') |
| | 405 | + for iw in interwiki: |
| | 406 | + self.wfile.write(iw+'<br/>') |
| | 407 | + self.wfile.write('</font>') |
| | 408 | + self.wfile.write('</td></tr></table>') |
| | 409 | + self.wfile.write('<hr>') |
| | 410 | + # show lower search bar |
| | 411 | + self.wfile.write(searchbar) |
| | 412 | + self.wfile.write('</body></html>') |
| | 413 | + except HTTPError: |
| | 414 | + self.send_error(400,'Bad request') |
| | 415 | + self.wfile.write("<div>Error in query</div>") |
| | 416 | + except URLError: |
| | 417 | + self.send_error(500,'Internal Server Error') |
| | 418 | + self.wfile.write("<div>Cannot connect to lucene search 2 daemon</div>") |
| | 419 | + delta_time = time.time() - start_time |
| | 420 | + print '[%s] Processed query %s in %d ms' %(time.strftime("%Y-%m-%d %H:%M:%S"),self.path,int(delta_time*1000)) |
| | 421 | + elif s[2] == '/': |
| | 422 | + # show the search form |
| | 423 | + f = open(curdir + sep + "searchForm.html") |
| | 424 | + search_form = f.read() |
| | 425 | + f.close() |
| | 426 | + self.send_response(200) |
| | 427 | + self.send_header('Cache-Control','no-cache') |
| | 428 | + self.send_header('Content-type','text/html') |
| | 429 | + self.end_headers() |
| | 430 | + self.wfile.write(search_form) |
| | 431 | + elif s[2] == '/prefixQuery': |
| | 432 | + # prefix search wrapper |
| | 433 | + params = {} |
| | 434 | + # parse key1=val1&key2=val2 syntax |
| | 435 | + params = cgi.parse_qs(s[4]) |
| | 436 | + query = '' |
| | 437 | + dbname = '' |
| | 438 | + namespaces = '' |
| | 439 | + for key,val in params.iteritems(): |
| | 440 | + if key == 'dbname': |
| | 441 | + dbname = val[0] |
| | 442 | + elif key == 'query': |
| | 443 | + query = val[0] |
| | 444 | + elif key == 'namespaces': |
| | 445 | + namespaces = val[0] |
| | 446 | + |
| | 447 | + if search_host.has_key(dbname): |
| | 448 | + host = search_host[dbname] |
| | 449 | + else: |
| | 450 | + host = search_host['<default>'] |
| | 451 | + |
| | 452 | + search_url = 'http://%s/prefix/%s/%s?format=json' % (host,dbname,urllib.quote(query)) |
| | 453 | + if namespaces != '': |
| | 454 | + search_url += '&namespaces=%s' % namespaces |
| | 455 | + |
| | 456 | + print(search_url) |
| | 457 | + |
| | 458 | + # forward json text |
| | 459 | + try: |
| | 460 | + results = urllib2.urlopen(search_url) |
| | 461 | + self.send_response(200) |
| | 462 | + self.send_header('Cache-Control','no-cache') |
| | 463 | + self.send_header('Content-type','text/html') |
| | 464 | + self.end_headers() |
| | 465 | + for line in results: |
| | 466 | + self.wfile.write(line) |
| | 467 | + except HTTPError: |
| | 468 | + self.send_error(400,'Bad request') |
| | 469 | + self.wfile.write("Error in query") |
| | 470 | + except URLError: |
| | 471 | + self.send_error(500,'Internal Server Error') |
| | 472 | + self.wfile.write("Cannot connect to lucene search 2 daemon") |
| | 473 | + else: |
| | 474 | + # showfile |
| | 475 | + f = open(curdir + s[2]) |
| | 476 | + file = f.read() |
| | 477 | + f.close() |
| | 478 | + self.send_response(200) |
| | 479 | + self.send_header('Cache-Control','no-cache') |
| | 480 | + self.send_header('Content-type','text/html') |
| | 481 | + self.end_headers() |
| | 482 | + self.wfile.write(file) |
| | 483 | + return |
| | 484 | + except IOError: |
| | 485 | + self.send_error(500,'Internal Server Error') |
| | 486 | + self.wfile.write('<a href="https://www.mediawiki.org/">Back</a>') |
| | 487 | + |
| | 488 | + |
| | 489 | + |
| | 490 | +try: |
| | 491 | + server = HTTPServer(('', 8080), MyHandler) |
| | 492 | + print 'Started webinterface at 8080...' |
| | 493 | + server.serve_forever() |
| | 494 | +except KeyboardInterrupt: |
| | 495 | + print '^C received, shutting down server' |
| | 496 | + server.socket.close() |
| | 497 | + |
| Index: trunk/lucene-search-3/src/main/webapp/webinterface/searchForm.html |
| — | — | @@ -0,0 +1,104 @@ |
| | 2 | +<html> |
| | 3 | +<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> |
| | 4 | +<link rel="stylesheet" type="text/css" media="screen,projection" href="https://www.mediawiki.org/lucenesearch.css" /> |
| | 5 | +<script type="text/javascript"> |
| | 6 | +var skin = "monobook"; |
| | 7 | +var stylepath = "/wiki-lucene/phase3/skins"; |
| | 8 | +var wgArticlePath = "/wiki-lucene/phase3/index.php/$1"; |
| | 9 | +var wgScriptPath = "/wiki-lucene/phase3"; |
| | 10 | +var wgScript = "/wiki-lucene/phase3/index.php"; |
| | 11 | +var wgServer = "http://localhost"; |
| | 12 | +var wgCanonicalNamespace = ""; |
| | 13 | +var wgCanonicalSpecialPageName = false; |
| | 14 | +var wgNamespaceNumber = 0; |
| | 15 | +var wgPageName = "Main_Page"; |
| | 16 | +var wgTitle = "Main Page"; |
| | 17 | +var wgAction = "view"; |
| | 18 | +var wgRestrictionEdit = []; |
| | 19 | +var wgRestrictionMove = []; |
| | 20 | +var wgArticleId = "1"; |
| | 21 | +var wgIsArticle = true; |
| | 22 | +var wgUserName = null; |
| | 23 | +var wgUserGroups = null; |
| | 24 | +var wgUserLanguage = "en"; |
| | 25 | +var wgContentLanguage = "en"; |
| | 26 | +var wgBreakFrames = false; |
| | 27 | +var wgCurRevisionId = "26709"; |
| | 28 | +</script> |
| | 29 | +<script type="text/javascript" src="/wikibits.js"></script> |
| | 30 | +<script type="text/javascript" src="/ajax.js"></script> |
| | 31 | +<script type="text/javascript"> |
| | 32 | + var wgLuceneAjaxSuggestWrapper="/prefixQuery"; |
| | 33 | + var wgDBname="enwiki"; |
| | 34 | +</script> |
| | 35 | +<script type="text/javascript" src="/luceneajaxsuggest.js"></script> |
| | 36 | +</head> |
| | 37 | +<body> |
| | 38 | + |
| | 39 | +<h2> Test web interface for lucene-search 2.1 </h2> |
| | 40 | + |
| | 41 | +Send comments to: Robert Stojnić (rainmansr@gmail.com) |
| | 42 | +</p> |
| | 43 | + |
| | 44 | +<p> |
| | 45 | +<strong>Status:</strong> Super-slow (doing some testing) |
| | 46 | +</p> |
| | 47 | +<strong>Search:</strong> |
| | 48 | +<hr> |
| | 49 | +<div id="globalWrapper"> |
| | 50 | +<form name="search" id="search" method="get" action="/search"> |
| | 51 | + |
| | 52 | +Wiki: |
| | 53 | + <select name="dbname" onchange="wgDBname=window.document.search.dbname.options[selectedIndex].text;"> |
| | 54 | + <option value="wikilucene">wikilucene</option> |
| | 55 | + <option value="enwiki">enwiki</option> |
| | 56 | + <option value="dewiki">dewiki</option> |
| | 57 | + <option value="frwiki">frwiki</option> |
| | 58 | + <option value="jawiki">jawiki</option> |
| | 59 | + <option value="itwiki">itwiki</option> |
| | 60 | + <option value="srwiki">srwiki</option> |
| | 61 | + <option value="ruwiki">ruwiki</option> |
| | 62 | + <option value="enwiktionary">enwiktionary</option> |
| | 63 | + <option value="enwikinews">enwikinews</option> |
| | 64 | + <option value="enwikisource">enwikisource</option> |
| | 65 | + <option value="enwikiquote">enwikiquote</option> |
| | 66 | + <option value="enwikibooks">enwikibooks</option> |
| | 67 | + <option value="enwikiversity">enwikiversity</option> |
| | 68 | + <option value="enwiktionary-exact">enwiktionary-exact</option> |
| | 69 | + <!-- <option value="jawikiquote">jawikiquote</option> |
| | 70 | + <option value="wikilucene">wikilucene</option> |
| | 71 | + <option value="wikidev">wikidev</option> --> |
| | 72 | + </select> |
| | 73 | + |
| | 74 | +Search for <input type='text' name="query" value="" size="30" id="lsearchbox" /> |
| | 75 | + <input type="submit" value="Search" /> |
| | 76 | + <hr> |
| | 77 | + |
| | 78 | +Default namespaces: |
| | 79 | + |
| | 80 | + <label><input type='checkbox' value="1" name="ns0" checked="checked" />(Main)</label> |
| | 81 | + <label><input type='checkbox' value="1" name="ns1" />Talk</label> |
| | 82 | + <label><input type='checkbox' value="1" name="ns2" />User</label> |
| | 83 | + <label><input type='checkbox' value="1" name="ns3" />User talk</label> |
| | 84 | + <label><input type='checkbox' value="1" name="ns4" />Wikipedia</label> |
| | 85 | + |
| | 86 | + <label><input type='checkbox' value="1" name="ns5" />Wikipedia talk</label> |
| | 87 | + <label><input type='checkbox' value="1" name="ns6" />Image</label> |
| | 88 | + <label><input type='checkbox' value="1" name="ns7" />Image talk</label> |
| | 89 | + <label><input type='checkbox' value="1" name="ns8" />MediaWiki</label> |
| | 90 | + <label><input type='checkbox' value="1" name="ns9" />MediaWiki talk</label> |
| | 91 | + <label><input type='checkbox' value="1" name="ns10" />Template</label> |
| | 92 | + |
| | 93 | + <label><input type='checkbox' value="1" name="ns11" />Template talk</label> |
| | 94 | + <label><input type='checkbox' value="1" name="ns12" />Help</label> |
| | 95 | + <label><input type='checkbox' value="1" name="ns13" />Help talk</label> |
| | 96 | + <label><input type='checkbox' value="1" name="ns14" />Category</label> |
| | 97 | + <label><input type='checkbox' value="1" name="ns15" />Category talk</label> |
| | 98 | + <label><input type='checkbox' value="1" name="ns100" />Portal</label> |
| | 99 | + <label><input type='checkbox' value="1" name="ns101" />Portal talk</label> |
| | 100 | + |
| | 101 | +</form> |
| | 102 | +<br><br><br><br><br><br><br><br><br><br><br> |
| | 103 | +</div> |
| | 104 | +</body> |
| | 105 | +</html> |
| Property changes on: trunk/lucene-search-3/src/main/webapp/webinterface |
| ___________________________________________________________________ |
| Added: svn:ignore |
| 1 | 106 | + *.js |
| *.css |