fix parse_si for Japanese excel files

fixes #141 h/t @tgfjt .  Original message:

using #parse_si 'Phonetic Properties' items for Japanese excel files,
the Phonetic items(KATAKANA) represents pronunciation hints of String(KANJI).

```xml
<si>
 <t>漢字(japanese KANJI)</t>
 <rPh>
  <t>フリガナ(this is KATAKANA for pronounciation:漢字)</t>
 </rPh>
</si>
```

It expected get '漢字' . but got '漢字フリガナ'.
so replace these string, because this can be caused by only `<rPh>`.
This commit is contained in:
Takashi Fujita 2014-10-30 14:59:08 +09:00 committed by SheetJS
parent ba1d2ea2be
commit d4829476f7
3 changed files with 3 additions and 3 deletions

View File

@ -157,7 +157,7 @@ function parse_si(x, opts) {
/* 18.4.4 r CT_RElt (Rich Text Run) */
else if((y = x.match(sirregex))) {
z.r = utf8read(x);
z.t = utf8read(unescapexml((x.match(sitregex)||[]).join("").replace(tagregex,"")));
z.t = utf8read(unescapexml((x.replace(/<rPh.*?>(.*?)<\/rPh>/g, '').match(sitregex)||[]).join("").replace(tagregex,"")));
if(html) z.h = parse_rs(z.r);
}
/* 18.4.3 phoneticPr CT_PhoneticPr (TODO: needed for Asian support) */

View File

@ -4581,7 +4581,7 @@ function parse_si(x, opts) {
/* 18.4.4 r CT_RElt (Rich Text Run) */
else if((y = x.match(sirregex))) {
z.r = utf8read(x);
z.t = utf8read(unescapexml((x.match(sitregex)||[]).join("").replace(tagregex,"")));
z.t = utf8read(unescapexml((x.replace(/<rPh.*?>(.*?)<\/rPh>/g, '').match(sitregex)||[]).join("").replace(tagregex,"")));
if(html) z.h = parse_rs(z.r);
}
/* 18.4.3 phoneticPr CT_PhoneticPr (TODO: needed for Asian support) */

View File

@ -4539,7 +4539,7 @@ function parse_si(x, opts) {
/* 18.4.4 r CT_RElt (Rich Text Run) */
else if((y = x.match(sirregex))) {
z.r = utf8read(x);
z.t = utf8read(unescapexml((x.match(sitregex)||[]).join("").replace(tagregex,"")));
z.t = utf8read(unescapexml((x.replace(/<rPh.*?>(.*?)<\/rPh>/g, '').match(sitregex)||[]).join("").replace(tagregex,"")));
if(html) z.h = parse_rs(z.r);
}
/* 18.4.3 phoneticPr CT_PhoneticPr (TODO: needed for Asian support) */