xref: /dokuwiki/_test/tests/Parsing/Markdown/gfm-spec/skip.php (revision 6b33ca93d31259cdb3d5ae2fc49b5215b6bde268)
1<?php
2
3/**
4 * GFM spec examples that GfmSpecTest should skip, keyed by example number
5 * (as numbered in spec.txt / the rendered spec).
6 *
7 * Add entries here ONLY for behavior DokuWiki has explicitly decided not to
8 * implement — not for features that are merely pending. Unimplemented
9 * features should show as real failures so they remain visible TODOs on
10 * the branch.
11 *
12 * Each value is a short human-readable reason that will appear in phpunit's
13 * skip output.
14 */
15
16return [
17    // --------------------------------------------------------------------
18    // CommonMark §6.2 flanking-delimiter analysis — deliberately not
19    // implemented. DokuWiki's regex lexer uses leftmost-match and cannot
20    // apply CommonMark's left/right-flanking rules that distinguish
21    // word-chars, whitespace, and punctuation for `*`/`_` delimiters, or
22    // the "multiple-of-3" rule for overlapping runs. These examples all
23    // rely on that machinery.
24    // --------------------------------------------------------------------
25
26    // Unicode whitespace in flanking context. Our `\s` is ASCII-only
27    // because the lexer doesn't set the PCRE `u` flag.
28    363 => 'Unicode whitespace (U+00A0) flanking — requires u-flag-aware regex',
29
30    // Punctuation-adjacent flanking for `*` / `_` / `**` / `__`
31    362 => 'flanking: punctuation-adjacent `*` (left-flanking vs. right-flanking)',
32    368 => 'flanking: punctuation-adjacent `_`',
33    372 => 'flanking: intraword `_` with punctuation inside',
34    377 => 'flanking: `*` followed by `(` requires punctuation-aware flanking',
35    378 => 'flanking: nested `*(*foo*)*` requires flanking + balanced-pair analysis',
36    382 => 'flanking: nested `_(_foo_)_` requires flanking + balanced-pair analysis',
37    389 => 'flanking: punctuation-adjacent `**`',
38    394 => 'flanking: punctuation-adjacent `__`',
39    401 => 'flanking: `**` followed by `(`',
40    404 => 'flanking: nested `*bar*` inside `**foo ... foo**` with punctuation',
41    407 => 'flanking: `__` followed by `(`',
42    470 => 'flanking: nested `*_foo_*` requires balanced-pair analysis',
43    472 => 'flanking: nested `_*foo*_` requires balanced-pair analysis',
44
45    // Intraword `__` strong (even multibyte) — flanking rule for `_` requires
46    // examining whether the delimiter run is word-boundary-flanking, which our
47    // simple lookbehind/lookahead approximation doesn't fully match.
48    395 => 'flanking: intraword `__` (`foo__bar__`) — left-flanking vs right-flanking',
49    396 => 'flanking: intraword `__` across digits (`5__6__78`)',
50    397 => 'flanking: intraword `__` with Cyrillic',
51    398 => 'flanking: `__foo, __bar__, baz__` — flanking + balanced pairing',
52    409 => 'flanking: `__foo__bar` — intraword close',
53    410 => 'flanking: intraword `__` with Cyrillic (leading)',
54    411 => 'flanking: `__foo__bar__baz__` — multiple `__` pairs with flanking',
55    412 => 'flanking: `__(bar)__.` — punctuation-adjacent',
56
57    // Overlapping / multiple-of-3 rule for runs
58    416 => 'CommonMark rule 9 (overlapping same-delimiter `_foo _bar_ baz_`)',
59    417 => 'CommonMark overlapping `_` / `__` with flanking',
60    418 => 'CommonMark overlapping `*foo *bar**` — multiple-of-3 rule',
61    419 => 'CommonMark nested `*foo **bar** baz*` — balanced-pair analysis',
62    421 => 'CommonMark overlapping `*foo**bar*` — multiple-of-3',
63    422 => 'CommonMark nested `***foo** bar*` — triple-delimiter analysis',
64    423 => 'CommonMark nested `*foo **bar***` — triple-delimiter analysis',
65    424 => 'CommonMark nested `*foo**bar***` — triple-delimiter analysis',
66    425 => 'CommonMark triple `foo***bar***baz` — triple-delimiter analysis',
67    426 => 'CommonMark long delimiter runs `foo******bar*********baz`',
68    427 => 'CommonMark deeply nested `*foo **bar *baz* bim** bop*`',
69    434 => 'CommonMark overlapping `__foo __bar__ baz__` — multiple-of-3',
70    435 => 'CommonMark `____foo__ bar__` — leading long delimiter run',
71    436 => 'CommonMark `**foo **bar****` — trailing long delimiter run',
72    439 => 'CommonMark nested `***foo* bar**` — triple-delimiter',
73    440 => 'CommonMark nested `**foo *bar***` — triple-delimiter',
74    441 => 'CommonMark deeply nested `**foo *bar **baz** bim* bop**`',
75
76    // `__foo_` / `_foo__` — mixing `_` and `__` requires flanking to decide
77    // which delimiter pairs open/close.
78    463 => 'flanking: `__foo_` — mixed `_`/`__` pairing',
79    464 => 'flanking: `_foo__` — mixed `_`/`__` pairing',
80    465 => 'flanking: `___foo__` — delimiter-run length analysis',
81    466 => 'flanking: `____foo_` — delimiter-run length analysis',
82    467 => 'flanking: `__foo___` — delimiter-run length analysis',
83    468 => 'flanking: `_foo____` — delimiter-run length analysis',
84
85    // Long delimiter runs require excess-drop logic (2 outer chars dropped
86    // from each side). Stack-based pairing needed — out of scope.
87    473 => 'CommonMark `****foo****` — excess-drop (4+4 → strong only)',
88    474 => 'CommonMark `____foo____` — excess-drop (4+4 → strong only)',
89    475 => 'CommonMark `******foo******` — excess-drop (6+6 → strong only)',
90    477 => 'CommonMark `_____foo_____` — excess-drop (5+5 → em+strong, 2 dropped each side)',
91
92    // Overlapping / crossing delimiters
93    478 => 'CommonMark `*foo _bar* baz_` — overlapping different delimiters',
94    479 => 'CommonMark `*foo __bar *baz bim__ bam*` — crossing delimiters',
95    480 => 'CommonMark `**foo **bar baz**` — overlapping same delimiter',
96];
97