# HG changeset patch
# User František Kučera <franta-hg@frantovo.cz>
# Date 1318868074 -7200
# Node ID c60625d581582e672c66e654d07195da256b94b9
# Parent cbf1a1153313a4297187ae2ff58bba6af02449d8
Drupal: textová část zpráv (text/plain), základní funkční verze (XSLT+Java).
diff -r cbf1a1153313 -r c60625d58158 helpers/mimeTextPart.xsl
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/helpers/mimeTextPart.xsl Mon Oct 17 18:14:34 2011 +0200
@@ -0,0 +1,199 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet version="2.0"
+ xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ xmlns:fn="http://www.w3.org/2005/xpath-functions"
+ xmlns:h="http://www.w3.org/1999/xhtml">
+ <xsl:output method="text" encoding="UTF-8"/>
+ <xsl:strip-space elements="*"/>
+
+ <xsl:output method="text" encoding="UTF-8"/>
+ <xsl:strip-space elements="*"/>
+
+ <xsl:variable name="urlBase" select="/h:html/h:head/h:base/@href"/>
+
+ <!-- Celý dokument -->
+ <xsl:template match="/">
+ <xsl:apply-templates select="h:html/h:body"/>
+ </xsl:template>
+
+ <xsl:template match="h:h1">
+ <xsl:value-of select="text()"/>
+ <xsl:text> </xsl:text>
+ <xsl:for-each select="1 to string-length(.)">#</xsl:for-each>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:h2">
+ <xsl:value-of select="text()"/>
+ <xsl:text> </xsl:text>
+ <xsl:for-each select="1 to string-length(.)">-</xsl:for-each>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:h3">
+ <xsl:for-each select="1 to 3">#</xsl:for-each>
+ <xsl:text> </xsl:text>
+ <xsl:value-of select="text()"/>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+
+ <xsl:template match="h:h4">
+ <xsl:for-each select="1 to 4">#</xsl:for-each>
+ <xsl:text> </xsl:text>
+ <xsl:value-of select="text()"/>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+
+ <xsl:template match="h:h5">
+ <xsl:for-each select="1 to 5">#</xsl:for-each>
+ <xsl:text> </xsl:text>
+ <xsl:value-of select="text()"/>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:h6">
+ <xsl:for-each select="1 to 6">#</xsl:for-each>
+ <xsl:text> </xsl:text>
+ <xsl:value-of select="text()"/>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+
+ <xsl:template match="h:p">
+ <xsl:apply-templates/>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:a">
+ <xsl:text>"</xsl:text>
+ <xsl:value-of select="text()"/>
+ <xsl:text>" <</xsl:text>
+ <xsl:choose>
+ <xsl:when test="matches(@href, '^(http:|https:|ftp:)')">
+ <xsl:value-of select="@href"/>
+ </xsl:when>
+ <xsl:when test="matches(@href, '^mailto:')">
+ <xsl:value-of select="substring-after(@href, 'mailto:')"/>
+ </xsl:when>
+ <xsl:otherwise>
+ <xsl:choose>
+ <xsl:when test="ends-with($urlBase, '/') or starts-with(@href, '/')">
+ <xsl:value-of select="concat($urlBase, @href)"/>
+ </xsl:when>
+ <xsl:otherwise>
+ <xsl:value-of select="concat($urlBase, '/', @href)"/>
+ </xsl:otherwise>
+ </xsl:choose>
+ </xsl:otherwise>
+ </xsl:choose>
+ <xsl:text>></xsl:text>
+ <xsl:if test="@title and not(matches(@title, '^\s*$'))">
+ <xsl:text> (</xsl:text>
+ <xsl:value-of select="@title"/>
+ <xsl:text>)</xsl:text>
+ </xsl:if>
+ </xsl:template>
+
+ <xsl:template match="h:img">
+ <xsl:variable name="obrázek">
+ <h:a href="{@src}" title="{@title}">Obrázek: <xsl:value-of select="@alt"/></h:a>
+ </xsl:variable>
+ <xsl:apply-templates select="$obrázek/node()"/>
+ </xsl:template>
+
+ <xsl:template match="h:strong|h:b">
+ <xsl:text>**</xsl:text>
+ <xsl:apply-templates/>
+ <xsl:text>**</xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:em|h:i">
+ <xsl:text>*</xsl:text>
+ <xsl:apply-templates/>
+ <xsl:text>*</xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:abbr[@title]">
+ <xsl:apply-templates/>
+ <xsl:text> (</xsl:text>
+ <xsl:value-of select="@title"/>
+ <xsl:text>)</xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:pre">
+ <xsl:text>--------------------------------</xsl:text>
+ <xsl:text> </xsl:text>
+ <xsl:apply-templates/>
+ <xsl:text> </xsl:text>
+ <xsl:text>--------------------------------</xsl:text>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:code">
+ <xsl:text>`</xsl:text>
+ <xsl:apply-templates/>
+ <xsl:text>`</xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:hr">
+ <xsl:text>----------------------------------------------------------------</xsl:text>
+ <xsl:text> </xsl:text>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:ul">
+ <xsl:apply-templates/>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:ul/h:li">
+ <xsl:text> - </xsl:text>
+ <xsl:apply-templates/>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+ <xsl:template match="h:ol">
+ <xsl:for-each select="h:li">
+ <xsl:value-of select="concat(' ', position(), ') ')"/>
+ <xsl:apply-templates/>
+ <xsl:text> </xsl:text>
+ </xsl:for-each>
+ <xsl:text> </xsl:text>
+ </xsl:template>
+
+
+ <!--
+ <xsl:template match="h:blockquote[matches(p/text(), '^(\"|„)')]">
+
+ </xsl:template>
+ -->
+
+ <xsl:template match="text()[not(parent::h:pre)]">
+ <xsl:if test="matches(., '^\s')">
+ <xsl:text> </xsl:text>
+ </xsl:if>
+ <xsl:value-of select="normalize-space(.)"/>
+ <xsl:if test="matches(., '\s$')">
+ <xsl:text> </xsl:text>
+ </xsl:if>
+ </xsl:template>
+
+
+ <xsl:template match="h:div[@class='wwwLinks']">
+ <xsl:text>-- </xsl:text>
+ <xsl:text> </xsl:text>
+ <xsl:apply-templates/>
+ </xsl:template>
+
+
+</xsl:stylesheet>
diff -r cbf1a1153313 -r c60625d58158 src/org/sonews/storage/DrupalMessage.java
--- a/src/org/sonews/storage/DrupalMessage.java Mon Oct 17 13:55:28 2011 +0200
+++ b/src/org/sonews/storage/DrupalMessage.java Mon Oct 17 18:14:34 2011 +0200
@@ -98,7 +98,9 @@
/** Plain text part */
MimeBodyPart textPart = new MimeBodyPart();
- textPart.setText(readPlainText(rs, xhtmlText));
+ String plainText = readPlainText(rs, xhtmlText);
+ textPart.setText(plainText);
+ //addHeader("Lines", String.valueOf(plainText.split("\n").length));
/**
* Thunderbirdu záleží, v jakém pořadí části jsou
@@ -114,10 +116,22 @@
}
private String readPlainText(ResultSet rs, String xhtmlText) {
- /**
- * TODO: převést na prostý text
- */
- return "TODO: obyčejný text\n(zatím čtěte XHTML verzi)";
+ try {
+ TransformerFactory tf = TransformerFactory.newInstance();
+ Transformer textTransformer = tf.newTransformer(new StreamSource(Resource.getAsStream("helpers/mimeTextPart.xsl")));
+
+ StringReader input = new StringReader(xhtmlText);
+ StringWriter output = new StringWriter(xhtmlText.length());
+ textTransformer.transform(new StreamSource(input), new StreamResult(output));
+
+ return output.toString();
+ } catch (Exception e) {
+ /**
+ * TODO: lepší ošetření chyby
+ */
+ log.log(Level.WARNING, "Error while transforming article to plain text", e);
+ return makeSimpleXHTML("Při transformaci příspěvku bohužel došlo k chybě.");
+ }
}
private String readXhtmlText(ResultSet rs) {
@@ -177,7 +191,13 @@
* TODO: refaktorovat, přesunout
*/
private static String tidyXhtml(String inputText) throws IOException {
- // https://sourceforge.net/tracker/index.php?func=detail&aid=3424437&group_id=27659&atid=390966
+ /*
+ * Viz https://sourceforge.net/tracker/index.php?func=detail&aid=3424437&group_id=27659&atid=390966
+ *
+ * TODO:
+ * - použít delší zástupný řetězec, ne jen jeden znak
+ * - umísťovat ho jen tam, kde už nějaký text je (ne mezi >\s*<)
+ */
inputText = inputText.replaceAll("\\n", "◆\n");
Runtime r = Runtime.getRuntime();