source: other-projects/meddle/trunk/meddle-fixup.js@ 31627

Last change on this file since 31627 was 31627, checked in by davidb, 7 years ago

Changed to static home page with choice of DL to go to. Initial Google Scholar support added

File size: 14.4 KB
Line 
1// MEDDLE version 0.9
2
3
4// Ligature lookup info:
5// https://en.wikipedia.org/wiki/List_of_precomposed_Latin_characters_in_Unicode
6// https://en.wikipedia.org/wiki/Typographic_ligature#Ligatures_in_Unicode_.28Latin_alphabets.29
7
8function trim(str)
9{
10 return str.replace(/^\s\s*/, '').replace(/\s\s*$/, '');
11}
12
13var ligature_map = {
14
15 "\uA732": "AA" ,
16 "\uA733": "aa" ,
17 "\u00C6": "AE" ,
18 "\u00E6": "ae" ,
19 "\uA734": "AO" ,
20 "\uA735": "ao" ,
21 "\uA736": "AU" ,
22 "\uA737": "au" ,
23 "\uA738": "AV" ,
24 "\uA739": "av" ,
25 // as above but with bar
26 "\uA73A": "AV" ,
27 "\uA73B": "av" ,
28 "\uA73C": "AY" ,
29 "\uA73D": "ay" ,
30 "\u1F670": "et" ,
31 "\uFB00": "ff" ,
32 "\uFB03": "ffi" ,
33 "\uFB04": "ffl" ,
34 "\uFB01": "fi" ,
35 "\uFB02": "fl" ,
36 "\u0152": "OE" ,
37 "\u0153": "oe" ,
38 "\uA74E": "OO" ,
39 "\uA74F": "oo" ,
40 "\u00DF": "Å¿s" ,
41 "\u00DF": "Å¿z" ,
42 "\uFB06": "st" ,
43 "\uFB05": "Å¿t" ,
44 "\uA728": "TZ" ,
45 "\uA729": "tz" ,
46 "\u1D6B": "ue" ,
47 "\uAB50": "ui" ,
48 "\uA760": "VY" ,
49 "\uA761": "vy"
50};
51
52var ligature_re = null;
53
54var accented = {
55 'a': '[Aa\xaa\xc0-\xc5\xe0-\xe5\u0100-\u0105\u01cd\u01ce\u0200-\u0203\u0226\u0227\u1d2c\u1d43\u1e00\u1e01\u1e9a\u1ea0-\u1ea3\u2090\u2100\u2101\u213b\u249c\u24b6\u24d0\u3371-\u3374\u3380-\u3384\u3388\u3389\u33a9-\u33af\u33c2\u33ca\u33df\u33ff\uff21\uff41]',
56 'b': '[Bb\u1d2e\u1d47\u1e02-\u1e07\u212c\u249d\u24b7\u24d1\u3374\u3385-\u3387\u33c3\u33c8\u33d4\u33dd\uff22\uff42]',
57 'c': '[Cc\xc7\xe7\u0106-\u010d\u1d9c\u2100\u2102\u2103\u2105\u2106\u212d\u216d\u217d\u249e\u24b8\u24d2\u3376\u3388\u3389\u339d\u33a0\u33a4\u33c4-\u33c7\uff23\uff43]',
58 'd': '[Dd\u010e\u010f\u01c4-\u01c6\u01f1-\u01f3\u1d30\u1d48\u1e0a-\u1e13\u2145\u2146\u216e\u217e\u249f\u24b9\u24d3\u32cf\u3372\u3377-\u3379\u3397\u33ad-\u33af\u33c5\u33c8\uff24\uff44]',
59 'e': '[Ee\xc8-\xcb\xe8-\xeb\u0112-\u011b\u0204-\u0207\u0228\u0229\u1d31\u1d49\u1e18-\u1e1b\u1eb8-\u1ebd\u2091\u2121\u212f\u2130\u2147\u24a0\u24ba\u24d4\u3250\u32cd\u32ce\uff25\uff45]',
60 'f': '[Ff\u1da0\u1e1e\u1e1f\u2109\u2131\u213b\u24a1\u24bb\u24d5\u338a-\u338c\u3399\ufb00-\ufb04\uff26\uff46]',
61 'g': '[Gg\u011c-\u0123\u01e6\u01e7\u01f4\u01f5\u1d33\u1d4d\u1e20\u1e21\u210a\u24a2\u24bc\u24d6\u32cc\u32cd\u3387\u338d-\u338f\u3393\u33ac\u33c6\u33c9\u33d2\u33ff\uff27\uff47]',
62 'h': '[Hh\u0124\u0125\u021e\u021f\u02b0\u1d34\u1e22-\u1e2b\u1e96\u210b-\u210e\u24a3\u24bd\u24d7\u32cc\u3371\u3390-\u3394\u33ca\u33cb\u33d7\uff28\uff48]',
63 'i': '[Ii\xcc-\xcf\xec-\xef\u0128-\u0130\u0132\u0133\u01cf\u01d0\u0208-\u020b\u1d35\u1d62\u1e2c\u1e2d\u1ec8-\u1ecb\u2071\u2110\u2111\u2139\u2148\u2160-\u2163\u2165-\u2168\u216a\u216b\u2170-\u2173\u2175-\u2178\u217a\u217b\u24a4\u24be\u24d8\u337a\u33cc\u33d5\ufb01\ufb03\uff29\uff49]',
64 'j': '[Jj\u0132-\u0135\u01c7-\u01cc\u01f0\u02b2\u1d36\u2149\u24a5\u24bf\u24d9\u2c7c\uff2a\uff4a]',
65 'k': '[Kk\u0136\u0137\u01e8\u01e9\u1d37\u1d4f\u1e30-\u1e35\u212a\u24a6\u24c0\u24da\u3384\u3385\u3389\u338f\u3391\u3398\u339e\u33a2\u33a6\u33aa\u33b8\u33be\u33c0\u33c6\u33cd-\u33cf\uff2b\uff4b]',
66 'l': '[Ll\u0139-\u0140\u01c7-\u01c9\u02e1\u1d38\u1e36\u1e37\u1e3a-\u1e3d\u2112\u2113\u2121\u216c\u217c\u24a7\u24c1\u24db\u32cf\u3388\u3389\u33d0-\u33d3\u33d5\u33d6\u33ff\ufb02\ufb04\uff2c\uff4c]',
67 'm': '[Mm\u1d39\u1d50\u1e3e-\u1e43\u2120\u2122\u2133\u216f\u217f\u24a8\u24c2\u24dc\u3377-\u3379\u3383\u3386\u338e\u3392\u3396\u3399-\u33a8\u33ab\u33b3\u33b7\u33b9\u33bd\u33bf\u33c1\u33c2\u33ce\u33d0\u33d4-\u33d6\u33d8\u33d9\u33de\u33df\uff2d\uff4d]',
68 'n': '[Nn\xd1\xf1\u0143-\u0149\u01ca-\u01cc\u01f8\u01f9\u1d3a\u1e44-\u1e4b\u207f\u2115\u2116\u24a9\u24c3\u24dd\u3381\u338b\u339a\u33b1\u33b5\u33bb\u33cc\u33d1\uff2e\uff4e]',
69 'o': '[Oo\xba\xd2-\xd6\xf2-\xf6\u014c-\u0151\u01a0\u01a1\u01d1\u01d2\u01ea\u01eb\u020c-\u020f\u022e\u022f\u1d3c\u1d52\u1ecc-\u1ecf\u2092\u2105\u2116\u2134\u24aa\u24c4\u24de\u3375\u33c7\u33d2\u33d6\uff2f\uff4f]',
70 'p': '[Pp\u1d3e\u1d56\u1e54-\u1e57\u2119\u24ab\u24c5\u24df\u3250\u3371\u3376\u3380\u338a\u33a9-\u33ac\u33b0\u33b4\u33ba\u33cb\u33d7-\u33da\uff30\uff50]',
71 'q': '[Qq\u211a\u24ac\u24c6\u24e0\u33c3\uff31\uff51]',
72 'r': '[Rr\u0154-\u0159\u0210-\u0213\u02b3\u1d3f\u1d63\u1e58-\u1e5b\u1e5e\u1e5f\u20a8\u211b-\u211d\u24ad\u24c7\u24e1\u32cd\u3374\u33ad-\u33af\u33da\u33db\uff32\uff52]',
73 's': '[Ss\u015a-\u0161\u017f\u0218\u0219\u02e2\u1e60-\u1e63\u20a8\u2101\u2120\u24ae\u24c8\u24e2\u33a7\u33a8\u33ae-\u33b3\u33db\u33dc\ufb06\uff33\uff53]',
74 't': '[Tt\u0162-\u0165\u021a\u021b\u1d40\u1d57\u1e6a-\u1e71\u1e97\u2121\u2122\u24af\u24c9\u24e3\u3250\u32cf\u3394\u33cf\ufb05\ufb06\uff34\uff54]',
75 'u': '[Uu\xd9-\xdc\xf9-\xfc\u0168-\u0173\u01af\u01b0\u01d3\u01d4\u0214-\u0217\u1d41\u1d58\u1d64\u1e72-\u1e77\u1ee4-\u1ee7\u2106\u24b0\u24ca\u24e4\u3373\u337a\uff35\uff55]',
76 'v': '[Vv\u1d5b\u1d65\u1e7c-\u1e7f\u2163-\u2167\u2173-\u2177\u24b1\u24cb\u24e5\u2c7d\u32ce\u3375\u33b4-\u33b9\u33dc\u33de\uff36\uff56]',
77 'w': '[Ww\u0174\u0175\u02b7\u1d42\u1e80-\u1e89\u1e98\u24b2\u24cc\u24e6\u33ba-\u33bf\u33dd\uff37\uff57]',
78 'x': '[Xx\u02e3\u1e8a-\u1e8d\u2093\u213b\u2168-\u216b\u2178-\u217b\u24b3\u24cd\u24e7\u33d3\uff38\uff58]',
79 'y': '[Yy\xdd\xfd\xff\u0176-\u0178\u0232\u0233\u02b8\u1e8e\u1e8f\u1e99\u1ef2-\u1ef9\u24b4\u24ce\u24e8\u33c9\uff39\uff59]',
80 'z': '[Zz\u0179-\u017e\u01f1-\u01f3\u1dbb\u1e90-\u1e95\u2124\u2128\u24b5\u24cf\u24e9\u3390-\u3394\uff3a\uff5a]'
81};
82
83function accent_fold(search_string)
84{
85 // tidy up any pre- or post- whitespace
86 search_string = trim(search_string);
87
88 // protect any string literals that are special RE characters
89 search_string = search_string.replace(/([|\(\)\[\{\}.+*?^$\\])/g,"\\$1");
90
91 // replace characters by their compositors
92 var accent_replacer = function(chr) {
93 if (chr.charCodeAt(0)>128) {
94 for (var base_c in accented) {
95 var letter_re = new RegExp(accented[base_c],'gi');
96 if (letter_re.test(chr)) {
97 // Got accented char
98 // => downgrade to base character
99 chr = base_c;
100 }
101 // otherwise, leave it alone
102 }
103 }
104 return chr;
105 }
106
107 search_string = search_string.replace(/\S/g,accent_replacer);
108 search_string = search_string.replace(/\\([|\(\)\[\{\}.+*?^$\\])/g,"$1");
109
110 search_string = search_string.replace(/\s+/g," ");
111
112 return search_string;
113}
114
115
116
117function fixupEncodeInput(form) {
118 console.log( "amcm-dl-fixup fixupEncodeInput(form) called" );
119
120 if (ligature_re === null) {
121 var ligature_str = Object.keys(ligature_map).join("|");
122 ligature_re = new RegExp(ligature_str);
123 }
124
125 //console.log("*** ligature_str = " + ligature_str);
126
127 var query_box_val = form.elements['query'].value;
128
129 var detected_ligatures = ligature_re.test(query_box_val);
130 if (detected_ligatures) {
131 //var do_replacement = confirm("Detected ligatures in query. Replace with individual characters?");
132 var do_replacement = $('#meddle-lig').is(":checked");
133
134 if (do_replacement) {
135 var query_chars = query_box_val.split("");
136 var query_chars_fixed = [];
137
138 for (var i=0; i<query_chars.length; i++) {
139 var c = query_chars[i];
140 if (ligature_map[c]) {
141 c = ligature_map[c];
142 }
143 query_chars_fixed.push(c);
144 }
145 query_box_val = query_chars_fixed.join("");
146 }
147 }
148
149 var do_accent_replacement = $('#meddle-acc').is(":checked");
150 if (do_accent_replacement) {
151 query_box_val = accent_fold(query_box_val);
152 }
153
154 // e.g., content.ftsec:(+capisco)
155
156 var query_box_val = query_box_val.replace(/^\s+/,"");
157 var query_box_words = query_box_val.split(/\s+/);
158
159 var query_box_val_plus = "";
160 var query_box_val_double = "";
161
162 for (var i=0; i<query_box_words.length; i++) {
163 if (i>0) {
164 query_box_val_plus += " ";
165 }
166 query_box_val_plus += "+" + query_box_words[i];
167
168 if (i>0) {
169 query_box_val_double += " " + query_box_words[i-1]+query_box_words[i];
170 }
171 }
172
173
174 form.elements['query'].value = "content.ftsec:(" + query_box_val_plus + query_box_val_double + ")";
175
176 return encodeInput(form);
177}
178
179function fixupSubmitIt() {
180 var search_where = $("#fld0 option:selected").text();
181 //console.log("**** search_where = " + search_where);
182 var x = 0;
183 var search_select = $("#fld"+x+" option:selected");
184 var search_where = search_select.text();
185
186 while (search_where) {
187 if (search_where == "Any field") {
188 //var sel_val = document.getElementById("fld" + x).selectedIndex].value;
189
190 //var thisField = document.getElementById("fld" + x).options[document.getElementById("fld" + x).selectedIndex].value;
191
192 $("#fld"+x).val('content.ftsec:');
193 //$("#fld0 option[value='content.ftsec:']").prop('selected', true);
194 //alert("changed menu");
195 }
196 x = x + 1;
197 search_select = $("#fld"+x+" option:selected");
198 search_where = search_select.text();
199 //console.log("*** search select = " + search_select.text());
200 //alert("ddd");
201 }
202 buildQuery();
203
204 return submitIt();
205}
206
207function meddleInfoBox() {
208
209 $('#_proxy_css_top_insertion').append('<form name="MeddleForm" style="padding-bottom: 20px;"><center><table cellpadding="5" border="1"><tbody><tr><td align="center"><img src="http://bedrock.resnet.cms.waikato.ac.nz/meddle/meddle-icon-large.png" width="64" height="64" /></td><td><b><font size="+1"><a href="https://bedrock.resnet.cms.waikato.ac.nz/meddle/">MEDDLE Proxy: ModifiED Digital Library Proxy</a></font></b><br /><div id="dlcontext"></div><div id="dlcontextoptions"</div></td></tr></tbody></table></center></form>');
210
211 // Icon image
212 // By VistaICO.com (VistaICO Toolbar Icons) [CC BY 3.0 ]
213
214
215 var dlcontextoptions = '<input id="meddle-lig" name="meddle-lig" type="checkbox"><label for="meddle-lig" style="display: inline">&nbsp;Ligature&nbsp;expansion</label>&nbsp;&nbsp;<input id="meddle-acc" name="meddle-acc" type="checkbox"><label for="meddle-acc" style="display: inline">&nbsp;Accent&nbsp;folding</label>';
216
217
218 //console.log("*** location = " + window.location.pathname);
219 var detected_dl = "";
220
221 var domain_match = window.location.pathname.match(/nph-proxy-meddle.cgi\/.*?https?\/(.*)$/);
222
223 if (domain_match.length>1) {
224 var real_domain = domain_match[1];
225 //console.log("*** real domain = " + real_domain);
226
227 if (real_domain.match(/^dl\.acm\.org\//)) {
228 detected_dl = "ACM DL (Meddled with to provide: full-text quicksearch, word-wrap protection)";
229 //dlcontextoptions += "&nbsp;&nbsp;Also ";
230 }
231 else if (real_domain.match(/^scholar\.google\.[a-z]+/)) {
232 detected_dl = "Google Scholar";
233 }
234 else if (real_domain.match(/^ieeexplore\.ieee\.org\//)) {
235 detected_dl = "IEEE Xplore";
236 }
237 }
238
239 if (detected_dl !== "") {
240 $('#dlcontext').html("<i>Detected:" + detected_dl + "</i>");
241 }
242
243 $('#dlcontextoptions').html('<font size="-1">'+dlcontextoptions+'</font>');
244
245}
246
247
248function acmdlFixupInit() {
249
250 console.log("amc-dl-fixup initiated");
251
252 var query_form = document.getElementsByName("qiksearch")[0];
253 if (query_form) {
254 query_form.setAttribute("onsubmit", "fixupEncodeInput(this) ; _proxy_jslib_flush_write_buffers();");
255 }
256
257/*
258 //var query_box = document.getElementsByName("query")[0];
259 //var query_box_val = query_box.getAttribute("value");
260 //query_box.setAttribute("value", "Foo");
261*/
262 var adv_query_form = document.getElementById("theform");
263 if (adv_query_form) {
264 // javascript:submitIt();
265 // javascript:; _proxy_jslib_proxify_html(submitIt())[0]
266
267 adv_query_form.setAttribute("action","javascript:fixupSubmitIt();");
268 }
269
270 var query_box = document.getElementsByName("query")[0];
271 if (query_box) {
272 var query_box_val = query_box.getAttribute("value");
273 query_box.setAttribute("value", query_box_val.replace(/content\.ftsec:\(\+(.*)\)/g,"$1"));
274 }
275
276 console.log("acm-dl-fixup DOM tweaks done");
277}
278
279
280function fixupGScholarSubmit(evt) {
281 //alert("Bar");
282 console.log( "gscholar-dl-fixup fixupEncodeInput(form) called" );
283
284 var event = evt || window.event;
285 form = event.target.id;
286
287 event.preventDefault(); // to stop the form from submitting
288
289 if (ligature_re === null) {
290 var ligature_str = Object.keys(ligature_map).join("|");
291 ligature_re = new RegExp(ligature_str);
292 }
293
294 //console.log("*** ligature_str = " + ligature_str);
295
296 //var query_box_val = form.elements['q'].value;
297 var query_box = document.getElementById("gs_hp_tsi");
298 var query_box_val = query_box.value;
299
300 var detected_ligatures = ligature_re.test(query_box_val);
301 if (detected_ligatures) {
302 //var do_replacement = confirm("Detected ligatures in query. Replace with individual characters?");
303 var do_replacement = $('#meddle-lig').is(":checked");
304
305 if (do_replacement) {
306 var query_chars = query_box_val.split("");
307 var query_chars_fixed = [];
308
309 for (var i=0; i<query_chars.length; i++) {
310 var c = query_chars[i];
311 if (ligature_map[c]) {
312 c = ligature_map[c];
313 }
314 query_chars_fixed.push(c);
315 }
316 query_box_val = query_chars_fixed.join("");
317 }
318 }
319
320 var do_accent_replacement = $('#meddle-acc').is(":checked");
321 if (do_accent_replacement) {
322 query_box_val = accent_fold(query_box_val);
323 }
324
325
326 //form.elements['q'].value = query_box_val;
327 query_box.value = query_box_val;
328
329 _proxy_jslib_flush_write_buffers();
330
331 var query_form = document.getElementsByName("f")[0];
332 query_form.submit();
333 //form.submit();
334}
335
336function gscholarFixupInit() {
337
338 console.log("gscholar-fixup initiated");
339
340 var query_form = document.getElementsByName("f")[0];
341 if (query_form) {
342 //query_form.setAttribute("onsubmit", "fixupGScholarSubmit(this) ; _proxy_jslib_flush_write_buffers();");
343 //query_form.setAttribute("onsubmit", fixupGScholarSubmit);
344 //query_form.setAttribute("onsubmit", 'function(evt) { fixupGoogleSubmit(evt,this) }');
345
346 query_form.onsubmit = fixupGScholarSubmit;
347/*
348function(evt) {
349 var event = evt || window.event;
350 fixupGScholarSubmit(event,event.target.id);
351
352 //console.log(event.target.id); // myform
353
354 }
355*/
356
357 }
358
359
360
361/*
362 //var query_box = document.getElementsByName("query")[0];
363 //var query_box_val = query_box.getAttribute("value");
364 //query_box.setAttribute("value", "Foo");
365*/
366 console.log("gscholar DOM tweaks done");
367}
368
369
370// Google Scholar
371// <input class="gs_in_txt" name="q" value="" data-iq="" id="gs_hp_tsi" size="57" maxlength="256" autocapitalize="off" autocomplete="off" aria-label="Search" dir="ltr" type="text">
372
373$(document).ready(function() {
374 console.log( "jquery DOM ready" );
375 meddleInfoBox();
376
377 acmdlFixupInit()
378 gscholarFixupInit()
379
380});
381
Note: See TracBrowser for help on using the repository browser.