| 1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471 |
1
1
1
7375
823
7375
700
700
7375
7375
1
11
11
11
45635
45635
45635
1214
700
1214
1214
56278
56254
24
3419
1292
3419
187099
180564
125406
55158
55158
55158
6535
5238
5238
4098
5238
5238
5238
1
1
2
2
178985
172451
6534
2186
440
2186
4
4
4
4
4
4
4
64
12
64
40
24
24
78
78
24
4
4
4
4
24
5
4
32
32
192
192
70
122
32
4
4
1
1
1
1
9
1
9
1
9
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
4
1
1
1
1
1
1
1
1
1
1
3
3
1
1
1
1
1
1
9
1
1
1
1
9
2
9
1
9
1
1
1
1
| "use strict";
var Datum = require("./Datum").Datum;
var FieldDBObject = require("./../FieldDBObject").FieldDBObject;
/**
* @class The LanguageDatum widget is the place where all linguistic data is
* entered; one at a time.
*
* @property {DatumField} transcription The transcription field generally
* corresponds to the first line in linguistic examples that can
* either be written in the language's orthography or a
* romanization of the language. An additional field can be added
* if the language has a non-roman script. (This was previously called the utterance field).
* @property {DatumField} gloss The gloss field corresponds to the gloss
* line in linguistic examples where the morphological details of
* the words are displayed.
* @property {DatumField} translation The translation field corresponds to
* the third line in linguistic examples where in general an
* English translation. An additional field can be added if
* translations into other languages is needed.
* @property {DatumField} judgement The judgement is the grammaticality
* judgement associated with the datum, so grammatical,
* ungrammatical, felicitous, unfelicitous etc.
* @property {AudioVisual} audioVideo LanguageDatums can be associated with an audio or video
* file.
* @property {Session} session The session provides details about the set of
* data elicited. The session will contain details such as date,
* language, consultant etc.
* @property {Comments} comments The comments is a collection of comments
* associated with the datum, this is meant for comments like on a
* blog, not necessarily notes, which can be encoded in a
* field.(Use Case: team discussing a particular datum)
* @property {DatumTags} datumtags The datum tags are a collection of tags
* associated with the datum. These are made completely by the
* user.They are like blog tags, a way for the user to make
* categories without make a hierarchical structure, and make
* datum easier for search.
* @property {Date} dateEntered The date the LanguageDatum was first saved.
* @property {Date} dateModified The date the LanguageDatum was last saved.
*
* @description The initialize function brings up the datum widget in small
* view with one set of datum fields. However, the datum widget
* can contain more than datum field set and can also be viewed
* in full screen mode.
*
* @name LanguageDatum
* @extends Datum
* @constructs
*/
var LanguageDatum = function LanguageDatum(options) {
if (!this._fieldDBtype) {
this._fieldDBtype = "LanguageDatum";
}
if (options && typeof options === "string") {
this.debug("Turning LanguageDatum " + options + " to an object");
options = {
orthography: options
};
}
this.debug("Constructing LanguageDatum: ", options);
Datum.apply(this, [options]);
};
LanguageDatum.prototype = Object.create(Datum.prototype, /** @lends LanguageDatum.prototype */ {
constructor: {
value: LanguageDatum
},
length: {
get: function() {
Iif (this.utterance) {
return this.utterance.length;
}
Eif (this.orthography) {
return this.orthography.length;
}
if (this.morphemes) {
return this.morphemes.length;
}
}
},
orthography: {
configurable: true,
get: function() {
Eif (this.fields && this.fields.orthography) {
this.debug(" getting orthography " + this._id + " to " + this.fields.orthography.value);
return this.fields.orthography.value;
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
if (!this.fields || !this.fields.orthography) {
this.addField("orthography");
}
this.debug(" Setting orthography " + this._id + " to " + value);
this.fields.orthography.value = value;
}
},
utterance: {
configurable: true,
get: function() {
if (this.fields && this.fields.utterance) {
return this.fields.utterance.value;
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
if (!this.fields || !this.fields.utterance) {
this.addField("utterance");
}
this.fields.utterance.value = value;
}
},
/**
* Morphemes of the datum, if morphemes is empty it will provide the utterance
* or the orthography as a last resort copy
*
* @return {String} morphemes, or utterance or orthography
*/
morphemes: {
configurable: true,
get: function() {
if (this.fields && this.fields.morphemes) {
if (this.fields.morphemes.value) {
return this.fields.morphemes.value;
}
var placeholder = this.utterance || this.orthography || FieldDBObject.DEFAULT_STRING;
this.debug("morphemes is not defined so using " + placeholder);
return placeholder + "";
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
this.debug("setting morphemes " + value);
if (!this.fields || !this.fields.morphemes) {
this.addField("morphemes");
}
this.debug(" this.fields.morphemes ", this.fields.morphemes);
this.fields.morphemes.value = value;
this.debug(" this.fields.morphemes.value ", this.fields.morphemes.value);
}
},
allomorphs: {
configurable: true,
get: function() {
Eif (this.fields && this.fields.allomorphs) {
return this.fields.allomorphs.value;
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
Iif (!this.fields || !this.fields.allomorphs) {
this.addField("allomorphs");
}
this.fields.allomorphs.value = value;
}
},
gloss: {
configurable: true,
get: function() {
if (this.fields && this.fields.gloss) {
return this.fields.gloss.value;
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
if (!this.fields || !this.fields.gloss) {
this.addField("gloss");
}
this.fields.gloss.value = value;
}
},
syntacticCategory: {
configurable: true,
get: function() {
if (this.fields && this.fields.syntacticCategory) {
return this.fields.syntacticCategory.value;
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
if (!this.fields || !this.fields.syntacticCategory) {
this.addField("syntacticCategory");
}
this.fields.syntacticCategory.value = value;
}
},
translation: {
configurable: true,
get: function() {
if (this.fields && this.fields.translation) {
return this.fields.translation.value;
} else {
return FieldDBObject.DEFAULT_STRING;
}
},
set: function(value) {
Iif (!this.fields || !this.fields.translation) {
this.addField("translation");
}
this.fields.translation.value = value;
}
},
igt: {
get: function() {
var igtLines = {},
parallelText = {},
tuples = [],
feederWord,
fullWord,
lengthOfLongestIGTLineInWords,
igtLine,
cellIndex,
tuple;
var punctuationToRemove = /[#?!,\/\(\)\*\#]/g;
var whiteSpaceSplit = /[ \t\n]+/;
// var leipzigSplit = /[=-]+/;
var cleanUngrammaticalitySubstitutions = false;
this.fields.map(function(field) {
if (field.type && field.type.indexOf("parallelText") > -1) {
parallelText[field.id] = field.value;
}
if (!field.type || field.type.indexOf("IGT") === -1) {
return;
}
var chunks = field.value.replace(/#?!.,\//g, "").split(whiteSpaceSplit);
chunks = chunks.map(function(chunk) {
Iif (cleanUngrammaticalitySubstitutions) {
// If the token it not null or the empty string
if (chunk) {
// Replace (*_) with _
feederWord = chunk.replace(/\(\*[^)]*\)/g, "$1");
// Replace *(_) with _
feederWord = feederWord.replace(/\*\(([^)]*)\)/, "$1");
// Remove all remaining punctuation
fullWord = feederWord.replace(punctuationToRemove, "");
chunk = fullWord;
}
}
// return chunk.split(leipzigSplit);
return chunk;
});
igtLines[field.id] = chunks;
});
this.debug("Collected all the IGT lines", igtLines);
this.debug("Collected all the Paralel Text lines", parallelText);
// Build triples
lengthOfLongestIGTLineInWords = 0;
for (igtLine in igtLines) {
if (igtLines[igtLine] && igtLines[igtLine].length > lengthOfLongestIGTLineInWords) {
lengthOfLongestIGTLineInWords = igtLines[igtLine].length;
}
}
// for each word
for (cellIndex = 0; cellIndex < lengthOfLongestIGTLineInWords; cellIndex++) {
tuple = {};
// for each row of the igt
for (igtLine in igtLines) {
this.debug("working on " + igtLine, igtLines[igtLine]);
if (igtLines[igtLine] && igtLines[igtLine].length > cellIndex && igtLines[igtLine][cellIndex]) {
tuple[igtLine] = igtLines[igtLine][cellIndex];
} else {
tuple[igtLine] = "";
}
}
tuples.push(tuple);
}
this.debug("IGT+ tuples", tuples);
return {
tuples: tuples,
parallelText: parallelText
};
},
set: function() {
this.warn("Setting the igt has to be copy pasted from one of the other codebases");
}
},
/**
* The LaTeXiT function automatically mark-ups an example in LaTeX code
* (\exg. \"a) and then copies it on the export modal so that when the user
* switches over to their LaTeX file they only need to paste it in.
*
* We did a poll on Facebook among EGGers, and other linguists we know and
* found that Linguex was very popular, and GB4E, so we did the export in
* GB4E.
*/
/* jshint ignore:start */
laTeXiT: {
value: function(showInExportModal) {
this.debug(showInExportModal);
//corpus's most frequent fields
var frequentFields;
Iif (this.application && this.application.corpus && this.application.corpus.frequentFields) {
frequentFields = this.application.corpus.frequentFields;
} else {
frequentFields = this.fields.map(function(field) {
return field.id
});
}
//this datum/datalist's datumfields and their names
var fields = this.fields.map(function(field) {
return field.value;
});
var fieldLabels = this.fields.map(function(field) {
return field.id;
});
//setting up for IGT case...
var judgementIndex = -1;
var judgement = "";
var utteranceIndex = -1;
var utterance = "";
var morphemesIndex = -1;
var morphemes = "";
var glossIndex = -1;
var gloss = "";
var translationIndex = -1;
var translation = "";
var result = "\n\\begin{exe} \n \\ex \[";
//IGT case:
Eif (this.datumIsInterlinearGlossText()) {
/* get the key pieces of the IGT and delete them from the fields and fieldLabels arrays*/
judgementIndex = fieldLabels.indexOf("judgement");
Eif (judgementIndex >= 0) {
judgement = fields[judgementIndex];
fieldLabels.splice(judgementIndex, 1);
fields.splice(judgementIndex, 1);
}
utteranceIndex = fieldLabels.indexOf("utterance");
Eif (utteranceIndex >= 0) {
utterance = fields[utteranceIndex];
fieldLabels.splice(utteranceIndex, 1);
fields.splice(utteranceIndex, 1);
}
morphemesIndex = fieldLabels.indexOf("morphemes");
Eif (morphemesIndex >= 0) {
morphemes = fields[morphemesIndex];
fieldLabels.splice(morphemesIndex, 1);
fields.splice(morphemesIndex, 1);
}
glossIndex = fieldLabels.indexOf("gloss");
Eif (glossIndex >= 0) {
gloss = fields[glossIndex];
fieldLabels.splice(glossIndex, 1);
fields.splice(glossIndex, 1);
}
translationIndex = fieldLabels.indexOf("translation");
Eif (translationIndex >= 0) {
translation = fields[translationIndex];
fieldLabels.splice(translationIndex, 1);
fields.splice(translationIndex, 1);
}
//print the main IGT, escaping special latex chars
/* ignore unnecessary escapement */
result = result + this.escapeLatexChars(judgement) + "\]\{" + this.escapeLatexChars(utterance) +
"\n \\gll " + this.escapeLatexChars(morphemes) + "\\\\" +
"\n " + this.escapeLatexChars(gloss) + "\\\\" +
"\n \\trans " + this.escapeLatexChars(translation) + "\}" +
"\n\\label\{\}";
}
//remove any empty fields from our arrays
for (var i = fields.length - 1; i >= 0; i--) {
if (!fields[i]) {
fields.splice(i, 1);
fieldLabels.splice(i, 1);
}
}
/*throughout this next section, print frequent fields and infrequent ones differently
frequent fields get latex'd as items in a description and infrequent ones are the same,
but commented out.*/
Eif (fields && (fields.length > 0)) {
var numInfrequent = 0;
for (var field in fields) {
Eif (frequentFields.indexOf(fieldLabels[field]) >= 0) {
break;
}
numInfrequent++;
}
Eif (numInfrequent !== fieldLabels.length) {
result = result + "\n \\begin\{description\}";
} else {
result = result + "\n% \\begin\{description\}";
}
for (field in fields) {
Eif (fields[field] && (frequentFields.indexOf(fieldLabels[field]) >= 0)) {
result = result + "\n \\item\[\\sc\{" + this.escapeLatexChars(fieldLabels[field]) + "\}\] " + this.escapeLatexChars(fields[field]);
} else if (fields[field]) {
/* If as a field that is designed for LaTex dont excape the LaTeX characters */
if (fieldLabels[field].toLowerCase().indexOf("latex") > -1) {
result = result + "\n " + fields[field];
} else {
result = result + "\n% \\item\[\\sc\{" + this.escapeLatexChars(fieldLabels[field]) + "\}\] " + this.escapeLatexChars(fields[field]);
}
}
}
Eif (numInfrequent !== fieldLabels.length) {
result = result + "\n \\end\{description\}";
} else {
result = result + "\n% \\end\{description\}";
}
}
result = result + "\n\\end{exe}\n\n";
return result;
}
},
/* jshint ignore:end */
datumIsInterlinearGlossText: {
value: function(fieldLabels) {
Eif (!fieldLabels) {
fieldLabels = this.fields.map(function(field) {
return field.id;
});
}
var utteranceOrMorphemes = false;
var gloss = false;
var trans = false;
for (var fieldLabel in fieldLabels) {
if (fieldLabels[fieldLabel] === "utterance" || fieldLabels[fieldLabel] === "morphemes") {
utteranceOrMorphemes = true;
}
if (fieldLabels[fieldLabel] === "gloss") {
gloss = true;
}
if (fieldLabels[fieldLabel] === "translation") {
trans = true;
}
}
Eif (gloss || utteranceOrMorphemes || trans) {
return true;
} else {
return false;
}
}
}
});
exports.LanguageDatum = LanguageDatum;
|