Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[next specification candidate] Fix CJK handling #291

Draft
wants to merge 2 commits into
base: master
Choose a base branch
from
Draft

[next specification candidate] Fix CJK handling #291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
887617b
Add CJK handling
tats-u Sep 9, 2024
726e9fb
Some extra tests
tats-u Sep 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 44 additions & 5 deletions lib/inlines.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,9 @@ var reHtmlTag = common.reHtmlTag;
var rePunctuation = new RegExp(
/^[!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~\p{P}\p{S}]/u);

var reCjk = /[\u2e80-\u4dbf\u4e00-\ua4cf\uf900-\ufaff\ufe10-\ufe1f\ufe30-\ufe6f\uff00-\uffee\u{1b000}-\u{1b16f}\u{20000}-\u{3ffff}\u{e0100}-\u{e01ef}]/u;
var reSVSWithCjk = /[\ufe00-\ufe02\ufe0e]/u;

var reLinkTitle = new RegExp(
'^(?:"(' +
ESCAPED_CHAR +
Expand Down Expand Up @@ -242,13 +245,31 @@ var parseHtmlTag = function(block) {
}
};

var beforeRuneAndPos = function(str, pos) {
if (pos <= 0) {
return ["\n", 0];
}
var beforeCharCode = str.charCodeAt(pos - 1);
if (beforeCharCode < 0xdc00 || beforeCharCode > 0xdfff || pos === 1) {
// not surrogate pair or starts with lower surrogate
return [str.charAt(pos - 1), pos - 1];
}
var twoBeforeCharCode = str.charCodeAt(pos - 2);
if (twoBeforeCharCode < 0xd800 || twoBeforeCharCode > 0xdbff) {
// lonely low surrogate
return [str.charAt(pos - 1), pos - 1];
}
// valid surrogate pair
return [str.substring(pos - 2, pos), pos - 2];
}

// Scan a sequence of characters with code cc, and return information about
// the number of delimiters and whether they are positioned such that
// they can open and/or close emphasis or strong emphasis. A utility
// function for strong/emph parsing.
var scanDelims = function(cc) {
var numdelims = 0;
var char_before, char_after, cc_after;
var char_before, char_before_pos, char_two_before, char_after, cc_after;
var startpos = this.pos;
var left_flanking, right_flanking, can_open, can_close;
var after_is_whitespace,
Expand All @@ -270,8 +291,17 @@ var scanDelims = function(cc) {
return null;
}

char_before = startpos === 0 ? "\n" : this.subject.charAt(startpos - 1);

[char_before, char_before_pos] = beforeRuneAndPos(this.subject, startpos);
// Seldom used, so use lazy evaluation
char_two_before = {
cached: undefined,
get(startpos, subject) {
if (this.cached === undefined) {
this.cached = beforeRuneAndPos(subject, startpos)[0];
}
return this.cached;
}
};
cc_after = this.peek();
if (cc_after === -1) {
char_after = "\n";
Expand All @@ -283,15 +313,24 @@ var scanDelims = function(cc) {
after_is_punctuation = rePunctuation.test(char_after);
before_is_whitespace = reUnicodeWhitespaceChar.test(char_before);
before_is_punctuation = rePunctuation.test(char_before);
var either_is_cjk =
reCjk.test(char_before) ||
reCjk.test(char_after) ||
(reSVSWithCjk.test(char_before) && reCjk.test(char_two_before.get(char_before_pos, this.subject)));

left_flanking =
!after_is_whitespace &&
(!after_is_punctuation ||
before_is_whitespace ||
before_is_punctuation);
before_is_punctuation ||
either_is_cjk);
right_flanking =
!before_is_whitespace &&
(!before_is_punctuation || after_is_whitespace || after_is_punctuation);
(!before_is_punctuation ||
after_is_whitespace ||
after_is_punctuation ||
either_is_cjk
);
if (cc === C_UNDERSCORE) {
can_open = left_flanking && (!right_flanking || before_is_punctuation);
can_close = right_flanking && (!left_flanking || after_is_punctuation);
Expand Down
17 changes: 16 additions & 1 deletion test/regression.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ Issue #108 - Chinese punctuation not recognized
```````````````````````````````` example
**。**话
.
<p>**。**话</p>
<p><strong>。</strong>话</p>
````````````````````````````````

Issue jgm/cmark#177 - incorrect emphasis parsing
Expand Down Expand Up @@ -518,3 +518,18 @@ foo <!-- test --> more -->
<p>foo <!-----></p>
<p>foo <!-- test --> more --&gt;</p>
````````````````````````````````

```````````````````````````````` example
𠮷**(U+20BB7)**

禰󠄀**(ね)**豆子

福︀**(福)**祉︀**(祉)**

**㊙︎**Top Secret**㊙︎**
.
<p>𠮷<strong>(U+20BB7)</strong></p>
<p>禰󠄀<strong>(ね)</strong>豆子</p>
<p>福︀<strong>(福)</strong>祉︀<strong>(祉)</strong></p>
<p><strong>㊙︎</strong>Top Secret<strong>㊙︎</strong></p>
````````````````````````````````
Loading