« get me outta code hell

transform-content.js « util « src - hsmusic-wiki - HSMusic - static wiki software cataloguing collaborative creation
about summary refs log tree commit diff
path: root/src/util/transform-content.js
blob: 454cb374438cdecebd7ef3709019b53af11dd2d0 (plain)
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
// See also replacer.js, which covers the actual syntax parser and node
// interpreter. This file works with replacer.js to provide higher-level
// interfaces for converting various content found in wiki data to HTML for
// display on the site.

export {transformInline} from './replacer.js';

export const replacerSpec = {
  album: {
    find: 'album',
    link: 'album',
  },
  'album-commentary': {
    find: 'album',
    link: 'albumCommentary',
  },
  'album-gallery': {
    find: 'album',
    link: 'albumGallery',
  },
  artist: {
    find: 'artist',
    link: 'artist',
  },
  'artist-gallery': {
    find: 'artist',
    link: 'artistGallery',
  },
  'commentary-index': {
    find: null,
    link: 'commentaryIndex',
  },
  date: {
    find: null,
    value: (ref) => new Date(ref),
    html: (date, {html, language}) =>
      html.tag('time',
        {datetime: date.toString()},
        language.formatDate(date)),
  },
  'flash-index': {
    find: null,
    link: 'flashIndex',
  },
  flash: {
    find: 'flash',
    link: 'flash',
    transformName(name, node, input) {
      const nextCharacter = input[node.iEnd];
      const lastCharacter = name[name.length - 1];
      if (![' ', '\n', '<'].includes(nextCharacter) && lastCharacter === '.') {
        return name.slice(0, -1);
      } else {
        return name;
      }
    },
  },
  group: {
    find: 'group',
    link: 'groupInfo',
  },
  'group-gallery': {
    find: 'group',
    link: 'groupGallery',
  },
  home: {
    find: null,
    link: 'home',
  },
  'listing-index': {
    find: null,
    link: 'listingIndex',
  },
  listing: {
    find: 'listing',
    link: 'listing',
  },
  media: {
    find: null,
    link: 'media',
  },
  'news-index': {
    find: null,
    link: 'newsIndex',
  },
  'news-entry': {
    find: 'newsEntry',
    link: 'newsEntry',
  },
  root: {
    find: null,
    link: 'root',
  },
  site: {
    find: null,
    link: 'site',
  },
  static: {
    find: 'staticPage',
    link: 'staticPage',
  },
  string: {
    find: null,
    value: (ref) => ref,
    html: (ref, {language, args}) => language.$(ref, args),
  },
  tag: {
    find: 'artTag',
    link: 'tag',
  },
  track: {
    find: 'track',
    link: 'track',
  },
};

function splitLines(text) {
  return text.split(/\r\n|\r|\n/);
}

function joinLineBreaks(sourceLines) {
  const outLines = [];

  let lineSoFar = '';
  for (let i = 0; i < sourceLines.length; i++) {
    const line = sourceLines[i];
    lineSoFar += line;
    if (!line.endsWith('<br>')) {
      outLines.push(lineSoFar);
      lineSoFar = '';
    }
  }

  if (lineSoFar) {
    outLines.push(lineSoFar);
  }

  return outLines;
}

function parseAttributes(string, {to}) {
  const attributes = Object.create(null);
  const skipWhitespace = (i) => {
    const ws = /\s/;
    if (ws.test(string[i])) {
      const match = string.slice(i).match(/[^\s]/);
      if (match) {
        return i + match.index;
      } else {
        return string.length;
      }
    } else {
      return i;
    }
  };

  for (let i = 0; i < string.length; ) {
    i = skipWhitespace(i);
    const aStart = i;
    const aEnd = i + string.slice(i).match(/[\s=]|$/).index;
    const attribute = string.slice(aStart, aEnd);
    i = skipWhitespace(aEnd);
    if (string[i] === '=') {
      i = skipWhitespace(i + 1);
      let end, endOffset;
      if (string[i] === '"' || string[i] === "'") {
        end = string[i];
        endOffset = 1;
        i++;
      } else {
        end = '\\s';
        endOffset = 0;
      }
      const vStart = i;
      const vEnd = i + string.slice(i).match(new RegExp(`${end}|$`)).index;
      const value = string.slice(vStart, vEnd);
      i = vEnd + endOffset;
      if (attribute === 'src' && value.startsWith('media/')) {
        attributes[attribute] = to('media.path', value.slice('media/'.length));
      } else {
        attributes[attribute] = value;
      }
    } else {
      attributes[attribute] = attribute;
    }
  }
  return Object.fromEntries(
    Object.entries(attributes).map(([key, val]) => [
      key,
      val === 'true'
        ? true
        : val === 'false'
        ? false
        : val === key
        ? true
        : val,
    ])
  );
}

function unbound_transformMultiline(text, {
  img,
  to,
  transformInline,

  thumb = null,
}) {
  // Heck yes, HTML magics.

  text = transformInline(text.trim());

  const outLines = [];

  const indentString = ' '.repeat(4);

  let levelIndents = [];
  const openLevel = (indent) => {
    // opening a sublist is a pain: to be semantically *and* visually
    // correct, we have to append the <ul> at the end of the existing
    // previous <li>
    const previousLine = outLines[outLines.length - 1];
    if (previousLine?.endsWith('</li>')) {
      // we will re-close the <li> later
      outLines[outLines.length - 1] = previousLine.slice(0, -5) + ' <ul>';
    } else {
      // if the previous line isn't a list item, this is the opening of
      // the first list level, so no need for indent
      outLines.push('<ul>');
    }
    levelIndents.push(indent);
  };
  const closeLevel = () => {
    levelIndents.pop();
    if (levelIndents.length) {
      // closing a sublist, so close the list item containing it too
      outLines.push(indentString.repeat(levelIndents.length) + '</ul></li>');
    } else {
      // closing the final list level! no need for indent here
      outLines.push('</ul>');
    }
  };

  // okay yes we should support nested formatting, more than one blockquote
  // layer, etc, but hear me out here: making all that work would basically
  // be the same as implementing an entire markdown converter, which im not
  // interested in doing lol. sorry!!!
  let inBlockquote = false;

  let lines = splitLines(text);
  lines = joinLineBreaks(lines);
  for (let line of lines) {
    const imageLine = line.startsWith('<img');
    line = line.replace(/<img (.*?)>/g, (match, attributes) =>
      img({
        lazy: true,
        link: true,
        thumb,
        ...parseAttributes(attributes, {to}),
      })
    );

    let indentThisLine = 0;
    let lineContent = line;
    let lineTag = 'p';

    const listMatch = line.match(/^( *)- *(.*)$/);
    if (listMatch) {
      // is a list item!
      if (!levelIndents.length) {
        // first level is always indent = 0, regardless of actual line
        // content (this is to avoid going to a lesser indent than the
        // initial level)
        openLevel(0);
      } else {
        // find level corresponding to indent
        const indent = listMatch[1].length;
        let i;
        for (i = levelIndents.length - 1; i >= 0; i--) {
          if (levelIndents[i] <= indent) break;
        }
        // note: i cannot equal -1 because the first indentation level
        // is always 0, and the minimum indentation is also 0
        if (levelIndents[i] === indent) {
          // same indent! return to that level
          while (levelIndents.length - 1 > i) closeLevel();
          // (if this is already the current level, the above loop
          // will do nothing)
        } else if (levelIndents[i] < indent) {
          // lesser indent! branch based on index
          if (i === levelIndents.length - 1) {
            // top level is lesser: add a new level
            openLevel(indent);
          } else {
            // lower level is lesser: return to that level
            while (levelIndents.length - 1 > i) closeLevel();
          }
        }
      }
      // finally, set variables for appending content line
      indentThisLine = levelIndents.length;
      lineContent = listMatch[2];
      lineTag = 'li';
    } else {
      // not a list item! close any existing list levels
      while (levelIndents.length) closeLevel();

      // like i said, no nested shenanigans - quotes only appear outside
      // of lists. sorry!
      const quoteMatch = line.match(/^> *(.*)$/);
      if (quoteMatch) {
        // is a quote! open a blockquote tag if it doesnt already exist
        if (!inBlockquote) {
          inBlockquote = true;
          outLines.push('<blockquote>');
        }
        indentThisLine = 1;
        lineContent = quoteMatch[1];
      } else if (inBlockquote) {
        // not a quote! close a blockquote tag if it exists
        inBlockquote = false;
        outLines.push('</blockquote>');
      }

      // let some escaped symbols display as the normal symbol, since the
      // point of escaping them is just to avoid having them be treated as
      // syntax markers!
      if (lineContent.match(/( *)\\-/)) {
        lineContent = lineContent.replace('\\-', '-');
      } else if (lineContent.match(/( *)\\>/)) {
        lineContent = lineContent.replace('\\>', '>');
      }
    }

    if (lineTag === 'p') {
      // certain inline element tags should still be postioned within a
      // paragraph; other elements (e.g. headings) should be added as-is
      const elementMatch = line.match(/^<(.*?)[ >]/);
      if (
        elementMatch &&
        !imageLine &&
        ![
          'a',
          'abbr',
          'b',
          'bdo',
          'br',
          'cite',
          'code',
          'data',
          'datalist',
          'del',
          'dfn',
          'em',
          'i',
          'img',
          'ins',
          'kbd',
          'mark',
          'output',
          'picture',
          'q',
          'ruby',
          'samp',
          'small',
          'span',
          'strong',
          'sub',
          'sup',
          'svg',
          'time',
          'var',
          'wbr',
        ].includes(elementMatch[1])
      ) {
        lineTag = '';
      }

      // for sticky headings!
      if (elementMatch && elementMatch[1] === 'h2') {
        lineContent = lineContent.replace(/<h2(.*?)>/g, (match, attributes) => {
          const parsedAttributes = parseAttributes(attributes, {to});
          return `<h2 ${html.attributes({
            ...parsedAttributes,
            class: [...parsedAttributes.class?.split(' ') ?? [], 'content-heading'],
          })}>`;
        });
      }
    }

    let pushString = indentString.repeat(indentThisLine);
    if (lineTag) {
      pushString += `<${lineTag}>${lineContent}</${lineTag}>`;
    } else {
      pushString += lineContent;
    }
    outLines.push(pushString);
  }

  // after processing all lines...

  // if still in a list, close all levels
  while (levelIndents.length) closeLevel();

  // if still in a blockquote, close its tag
  if (inBlockquote) {
    inBlockquote = false;
    outLines.push('</blockquote>');
  }

  return outLines.join('\n');
}

function unbound_transformLyrics(text, {
  transformInline,
  transformMultiline,
}) {
  // Different from transformMultiline 'cuz it joins multiple lines together
  // with line 8reaks (<br>); transformMultiline treats each line as its own
  // complete paragraph (or list, etc).

  // If it looks like old data, then like, oh god.
  // Use the normal transformMultiline tool.
  if (text.includes('<br')) {
    return transformMultiline(text);
  }

  text = transformInline(text.trim());

  let buildLine = '';
  const addLine = () => outLines.push(`<p>${buildLine}</p>`);
  const outLines = [];
  for (const line of text.split('\n')) {
    if (line.length) {
      if (buildLine.length) {
        buildLine += '<br>';
      }
      buildLine += line;
    } else if (buildLine.length) {
      addLine();
      buildLine = '';
    }
  }
  if (buildLine.length) {
    addLine();
  }
  return outLines.join('\n');
}

export {
  unbound_transformLyrics as transformLyrics,
  unbound_transformMultiline as transformMultiline
}