fix(markdown): do not merge continuous cjk if proseWrap=preserve (#4504)

* test: add tests

* fix(markdown): do not merge continuous cjk if proseWrap=preserve

* fix: remove trailing comma for node4
master
Ika 2018-05-19 13:53:34 +08:00 committed by GitHub
parent ea01781d8c
commit a9eb68296c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 36 additions and 9 deletions

View File

@ -612,15 +612,17 @@ function getMaxContinuousCount(str, target) {
* @param {string} text
* @return {Array<{ type: "whitespace", value: " " | "\n" | "" } | { type: "word", value: string }>}
*/
function splitText(text) {
function splitText(text, options) {
const KIND_NON_CJK = "non-cjk";
const KIND_CJK_CHARACTER = "cjk-character";
const KIND_CJK_PUNCTUATION = "cjk-punctuation";
const nodes = [];
text
.replace(new RegExp(`(${cjkPattern})\n(${cjkPattern})`, "g"), "$1$2")
(options.proseWrap === "preserve"
? text
: text.replace(new RegExp(`(${cjkPattern})\n(${cjkPattern})`, "g"), "$1$2")
)
.split(/([ \t\n]+)/)
.forEach((token, index, tokens) => {
// whitespace

View File

@ -19,7 +19,7 @@ const util = require("../common/util");
* interface Sentence { children: Array<Word | Whitespace> }
* interface InlineCode { children: Array<Sentence> }
*/
function parse(text /*, parsers, opts*/) {
function parse(text, parsers, opts) {
const processor = unified()
.use(remarkParse, { footnotes: true, commonmark: true })
.use(frontmatter)
@ -27,7 +27,7 @@ function parse(text /*, parsers, opts*/) {
.use(restoreUnescapedCharacter(text))
.use(mergeContinuousTexts)
.use(transformInlineCode)
.use(splitText);
.use(splitText(opts));
return processor.runSync(processor.parse(text));
}
@ -102,8 +102,8 @@ function mergeContinuousTexts() {
});
}
function splitText() {
return ast =>
function splitText(options) {
return () => ast =>
map(ast, (node, index, parentNode) => {
if (node.type !== "text") {
return node;
@ -123,7 +123,7 @@ function splitText() {
return {
type: "sentence",
position: node.position,
children: util.splitText(value)
children: util.splitText(value, options)
};
});
}

View File

@ -55,7 +55,8 @@ function genericPrint(path, options, print) {
options.originalText.slice(
node.position.start.offset,
node.position.end.offset
)
),
options
)
.map(
node =>

View File

@ -12,6 +12,10 @@ This ia an english paragraph with a CJK quote "中文".
This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点\`...\`)。
::: warning 注意
该网站在国外无法访问,故以下演示无效
:::
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
這是一段很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長
很長的段落
@ -36,6 +40,8 @@ This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点\`...\`)。
::: warning 注意该网站在国外无法访问,故以下演示无效 :::
`;
exports[`cjk.md 2`] = `
@ -50,6 +56,10 @@ This ia an english paragraph with a CJK quote "中文".
This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点\`...\`)。
::: warning 注意
该网站在国外无法访问,故以下演示无效
:::
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
這是一段很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長的段落
@ -63,6 +73,8 @@ This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点\`...\`)。
::: warning 注意该网站在国外无法访问,故以下演示无效 :::
`;
exports[`cjk.md 3`] = `
@ -77,6 +89,10 @@ This ia an english paragraph with a CJK quote "中文".
This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点\`...\`)。
::: warning 注意
该网站在国外无法访问,故以下演示无效
:::
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
這是一段很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長很長的段落
@ -90,6 +106,10 @@ This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点\`...\`)。
::: warning 注意
该网站在国外无法访问,故以下演示无效
:::
`;
exports[`inline-nodes.md 1`] = `

View File

@ -9,3 +9,7 @@ This ia an english paragraph with a CJK quote "中文".
This ia an english paragraph with a CJK quote “中文“.
扩展运算符spread是三个点`...`)。
::: warning 注意
该网站在国外无法访问,故以下演示无效
:::