Closed
Description
Japanese or Chines language utf-8 not supporting in doc reading
example 1 にっぽんこく、にほんこ
example 2 監警會決定不在司法覆核裁決前發布首份階段性報告
such kind of languages is not reading in doc format
Steps to Reproduce
function phpReader($source) {
$phpWord = \PhpOffice\PhpWord\IOFactory::load($source, 'MsDoc');
$text = ExtractText($phpWord);
return $txt ;
}
function ExtractText($obj, $nested = 0) {
$txt = "";
if (method_exists($obj, 'getSections')) {
foreach ($obj->getSections() as $section) {
$txt .= " " . ExtractText($section, $nested + 1);
}
} else if (method_exists($obj, 'getElements')) {
foreach ($obj->getElements() as $element) {
$txt .= " " . ExtractText($element, $nested + 1);
}
} else if (method_exists($obj, 'getText')) {
$txt .= $obj->getText();
} else if (method_exists($obj, 'getRows')) {
foreach ($obj->getRows() as $row) {
$txt .= " " . ExtractText($row, $nested + 1);
}
} else if (method_exists($obj, 'getCells')) {
foreach ($obj->getCells() as $cell) {
$txt .= " " . ExtractText($cell, $nested + 1);
}
} else if (get_class($obj) != "PhpOffice\PhpWord\Element\TextBreak") {
$txt .= "(" . get_class($obj) . ")"; # unknown object, you need to add it
}
return $txt;
}
example1 responce is "k0c0}0�0S0 O k { � S "
example2 responce is " ãvf��gzl�[ N(WøSÕl��8hÁ �z"
- PHPWord Version: 2020
$phpWord response in example 2 .
like
` ```
PhpOffice\PhpWord\PhpWord Object
(
[sections:PhpOffice\PhpWord\PhpWord:private] => Array
(
[0] => PhpOffice\PhpWord\Element\Section Object
(
[container:protected] => Section
[style:PhpOffice\PhpWord\Element\Section:private] => PhpOffice\PhpWord\Style\Section Object
(
[orientation:PhpOffice\PhpWord\Style\Section:private] => portrait
[paper:PhpOffice\PhpWord\Style\Section:private] => PhpOffice\PhpWord\Style\Paper Object
(
[sizes:PhpOffice\PhpWord\Style\Paper:private] => Array
(
[A3] => Array
(
[0] => 297
[1] => 420
[2] => mm
)
[A4] => Array
(
[0] => 210
[1] => 297
[2] => mm
)
[A5] => Array
(
[0] => 148
[1] => 210
[2] => mm
)
[B5] => Array
(
[0] => 176
[1] => 250
[2] => mm
)
[Folio] => Array
(
[0] => 8.5
[1] => 13
[2] => in
)
[Legal] => Array
(
[0] => 8.5
[1] => 14
[2] => in
)
[Letter] => Array
(
[0] => 8.5
[1] => 11
[2] => in
)
)
[size:PhpOffice\PhpWord\Style\Paper:private] => A4
[width:PhpOffice\PhpWord\Style\Paper:private] => 11905.511811024
[height:PhpOffice\PhpWord\Style\Paper:private] => 16837.795275591
[styleName:protected] =>
[index:protected] =>
[aliases:protected] => Array
(
)
[isAuto:PhpOffice\PhpWord\Style\AbstractStyle:private] =>
)
[pageSizeW:PhpOffice\PhpWord\Style\Section:private] => 11905.511811024
[pageSizeH:PhpOffice\PhpWord\Style\Section:private] => 16837.795275591
[marginTop:PhpOffice\PhpWord\Style\Section:private] => 1440
[marginLeft:PhpOffice\PhpWord\Style\Section:private] => 1440
[marginRight:PhpOffice\PhpWord\Style\Section:private] => 1440
[marginBottom:PhpOffice\PhpWord\Style\Section:private] => 1440
[gutter:PhpOffice\PhpWord\Style\Section:private] => 0
[headerHeight:PhpOffice\PhpWord\Style\Section:private] => 720
[footerHeight:PhpOffice\PhpWord\Style\Section:private] => 720
[pageNumberingStart:PhpOffice\PhpWord\Style\Section:private] =>
[colsNum:PhpOffice\PhpWord\Style\Section:private] => 1
[colsSpace:PhpOffice\PhpWord\Style\Section:private] => 720
[breakType:PhpOffice\PhpWord\Style\Section:private] =>
[lineNumbering:PhpOffice\PhpWord\Style\Section:private] =>
[vAlign:PhpOffice\PhpWord\Style\Section:private] =>
[borderTopSize:protected] =>
[borderTopColor:protected] =>
[borderTopStyle:protected] =>
[borderLeftSize:protected] =>
[borderLeftColor:protected] =>
[borderLeftStyle:protected] =>
[borderRightSize:protected] =>
[borderRightColor:protected] =>
[borderRightStyle:protected] =>
[borderBottomSize:protected] =>
[borderBottomColor:protected] =>
[borderBottomStyle:protected] =>
[styleName:protected] =>
[index:protected] =>
[aliases:protected] => Array
(
)
[isAuto:PhpOffice\PhpWord\Style\AbstractStyle:private] =>
)
[headers:PhpOffice\PhpWord\Element\Section:private] => Array
(
)
[footers:PhpOffice\PhpWord\Element\Section:private] => Array
(
)
[footnoteProperties:PhpOffice\PhpWord\Element\Section:private] =>
[elements:protected] => Array
(
[0] => PhpOffice\PhpWord\Element\Text Object
(
[text:protected] => ãvf��gzl�[
[fontStyle:protected] => PhpOffice\PhpWord\Style\Font Object
(
[aliases:protected] => Array
(
[line-height] => lineHeight
[letter-spacing] => spacing
)
[type:PhpOffice\PhpWord\Style\Font:private] => text
[name:PhpOffice\PhpWord\Style\Font:private] => Songti SC
[hint:PhpOffice\PhpWord\Style\Font:private] =>
[size:PhpOffice\PhpWord\Style\Font:private] =>
[color:PhpOffice\PhpWord\Style\Font:private] => 000000
[bold:PhpOffice\PhpWord\Style\Font:private] => 1
[italic:PhpOffice\PhpWord\Style\Font:private] =>
[underline:PhpOffice\PhpWord\Style\Font:private] => none
[superScript:PhpOffice\PhpWord\Style\Font:private] =>
[subScript:PhpOffice\PhpWord\Style\Font:private] =>
[strikethrough:PhpOffice\PhpWord\Style\Font:private] =>
[doubleStrikethrough:PhpOffice\PhpWord\Style\Font:private] =>
[smallCaps:PhpOffice\PhpWord\Style\Font:private] =>
[allCaps:PhpOffice\PhpWord\Style\Font:private] =>
[fgColor:PhpOffice\PhpWord\Style\Font:private] =>
[scale:PhpOffice\PhpWord\Style\Font:private] =>
[spacing:PhpOffice\PhpWord\Style\Font:private] =>
[kerning:PhpOffice\PhpWord\Style\Font:private] =>
[paragraph:PhpOffice\PhpWord\Style\Font:private] =>
```