Last active
December 22, 2015 05:49
-
-
Save edouard-lopez/6426512 to your computer and use it in GitHub Desktop.
Slow processing when using saxon9HE.jar (20 files generated on ~40s, 1 every 2s).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
scriptDir="$(dirname "$0")" # emplacement du script | |
. "$scriptDir"/envrc # project variables | |
inputFile="${2:-"$HPF_UNIHAN_READING_SHORT"}" | |
while IFS=';' read -r unicode hanzi pinyin; | |
do | |
outputFile="$HPF_SVGTEXT_DIR/$hanzi-x${unicode#U+*}.svg" | |
printf "creating: %s\n" "$outputFile" | |
xsltproc -o "$outputFile" \ | |
--stringparam unicode "$unicode" \ | |
--stringparam hanzi "$hanzi" \ | |
--stringparam pinyin "$pinyin" \ | |
"$HPF_XSLT_CSV2SVG" "$HPF_TPL_SVGTEXT" | |
done < "$inputFile" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?xml version="1.0" encoding="UTF-8"?> | |
<!-- | |
@description | |
Place hanzi and pinyin in the correct element | |
@upstream: true | |
--> | |
<xsl:stylesheet version="2.0" | |
xmlns="http://www.w3.org/2000/svg" | |
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" | |
xmlns:xs="http://www.w3.org/2001/XMLSchema" | |
exclude-result-prefixes="#default xsl xs" | |
> | |
<!-- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ --> | |
<!-- ++++++++++++++++++++++++++ CONSTANT +++++++++++++++++++++++++ --> | |
<!-- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ --> | |
<xsl:variable name="emptyString" select="''" /> | |
<!-- When we want to strip content using a CLASS --> | |
<xsl:param name="hanzi" select="NO-HANZI" /> | |
<xsl:param name="pinyin" select="NO-PINYIN" /> | |
<!-- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ --> | |
<!-- ++++++++++++++++++++++++++ TEMPLATE +++++++++++++++++++++++++ --> | |
<!-- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ --> | |
<xsl:template match="/"> | |
<xsl:message>WIP: <xsl:value-of select="$hanzi" />/<xsl:value-of select="$pinyin" />/</xsl:message> | |
<!-- font/glyph/@glyph-name --> | |
<!-- font/glyph/@unicode --> | |
<xsl:apply-templates /> | |
</xsl:template> | |
<xsl:template match="*[@id='hanzi-glyph']/text()"> | |
<xsl:value-of select="$hanzi" /> | |
</xsl:template> | |
<xsl:template match="*[@id='pinyin-text']"> | |
<xsl:value-of select="$pinyin" /> | |
</xsl:template> | |
<xsl:template match="@*|node()"> | |
<xsl:copy> | |
<xsl:apply-templates select="@*|node()"/> | |
</xsl:copy> | |
</xsl:template> | |
</xsl:stylesheet> |
We can make this file beautiful and searchable if this error is corrected: No commas found in this CSV file in line 0.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
U+3400;㐀;qiū | |
U+3401;㐁;tiàn | |
U+3404;㐄;kuà | |
U+3405;㐅;wǔ | |
U+3406;㐆;yǐn | |
U+340C;㐌;yí | |
U+3416;㐖;xié | |
U+341C;㐜;chóu | |
U+3421;㐡;nuò | |
U+3424;㐤;dān |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I end up using
xsltproc
instead ofsaxon
: