folia2html: Implemented support for outputting based on other text cl…

…asses #30

foliatools/__init__.py

@@ -1,3 +1,3 @@
 """FoLiA-tools contains various Python-based command line tools for working with FoLiA XML (Format for Linguistic Annotation)"""
 
-VERSION = "2.4.7"
+VERSION = "2.4.8"

foliatools/folia2html.xsl

@@ -2,6 +2,7 @@
 <xsl:stylesheet version="1.0" xmlns="http://www.w3.org/1999/xhtml" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:imdi="http://www.mpi.nl/IMDI/Schema/IMDI" xmlns:folia="http://ilk.uvt.nl/folia" xmlns:exsl="http://exslt.org/common" xmlns:dc="http://purl.org/dc/elements/1.1/">
 
 <xsl:param name="css"></xsl:param>
+<xsl:param name="textclass">current</xsl:param>
 
 <xsl:output method="html" encoding="UTF-8" omit-xml-declaration="yes" doctype-public="-//W3C//DTD XHTML 1.0 Strict//EN" doctype-system="http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd" indent="yes" />
 
@@ -538,12 +539,12 @@
 
 <xsl:variable name="ancestors_ok">not(ancestor::folia:original) and not(ancestor::folia:suggestion) and not(ancestor::folia:alt) and not(ancestor::folia:altlayers)</xsl:variable><!-- Checks if all ancestors are authoritative -->
 <xsl:variable name="ancestors_nosubtoken">not(ancestor::folia:morpheme) and not(ancestor::folia:phoneme)</xsl:variable><!-- Checks if all ancestors are authoritative -->
-<xsl:variable name="textclass_current">(not(@class) or (@class='current'))</xsl:variable>
+<xsl:variable name="textclass_ok">((($textclass="current") and not(@class)) or (@class=$textclass))</xsl:variable>
 
 <xsl:template match="folia:w">
     <xsl:variable name="wid" select="@xml:id" />
     <xsl:if test="$ancestors_ok">
-        <span id="{@xml:id}"><xsl:attribute name="class">word<xsl:if test="//folia:wref[@id=$wid and not(ancestor::folia:altlayers)]"> sh</xsl:if><xsl:if test=".//folia:correction or .//folia:errordetection"> cor</xsl:if></xsl:attribute><span class="t"><xsl:value-of select="string(.//folia:t[$ancestors_ok and $ancestors_nosubtoken and not(ancestor::folia:str) and (not(@class) or @class = 'current')])"/></span><xsl:call-template name="inlineannotations" /></span>
+        <span id="{@xml:id}"><xsl:attribute name="class">word<xsl:if test="//folia:wref[@id=$wid and not(ancestor::folia:altlayers)]"> sh</xsl:if><xsl:if test=".//folia:correction or .//folia:errordetection"> cor</xsl:if></xsl:attribute><span class="t"><xsl:value-of select="string(.//folia:t[$ancestors_ok and $ancestors_nosubtoken and not(ancestor::folia:str) and $textclass_ok])"/></span><xsl:call-template name="inlineannotations" /></span>
     <xsl:choose>
        <xsl:when test="@space = 'no'"></xsl:when>
        <xsl:otherwise>
@@ -560,7 +561,7 @@
     <!-- Test presence of text in deeper structure elements, if they exist we don't
          render this text but rely on the text in the deeper structure  -->
     <!-- Next, check if text element is authoritative (ancestors_ok) and have the proper class -->
-    <xsl:if test="not(following-sibling::*//folia:t[$textclass_current and $ancestors_ok and $ancestors_nosubtoken and not(ancestor::folia:str)])"><xsl:if test="$textclass_current and $ancestors_ok and $ancestors_nosubtoken and not(ancestor::folia:str)"><xsl:apply-templates /></xsl:if></xsl:if>
+    <xsl:if test="not(following-sibling::*//folia:t[$textclass_ok and $ancestors_ok and $ancestors_nosubtoken and not(ancestor::folia:str)])"><xsl:if test="$textclass_current and $ancestors_ok and $ancestors_nosubtoken and not(ancestor::folia:str)"><xsl:apply-templates /></xsl:if></xsl:if>
 </xsl:template>
 
 

foliatools/xslt.py

@@ -39,6 +39,7 @@ def usage():
     print("  -E [extension]               Set extension (default: xml)",file=sys.stderr)
     print("  -q                           Ignore errors",file=sys.stderr)
     print("  -s [url]                     Associate a CSS Stylesheet (URL, may be relative)",file=sys.stderr)
+    print("  -t [textclass]               Text class to output",file=sys.stderr)
 
 
 
@@ -52,6 +53,7 @@ class settings:
     outputextension = 'UNDEFINED'
     usage = "UNDEFINED"
     css = ""
+    textclass = "current"
 
 def processdir(d, outputfilename = None):
     print("Searching in  " + d, file=sys.stderr)
@@ -64,10 +66,11 @@ def processdir(d, outputfilename = None):
 
 def process(inputfilename, outputfilename=None):
     try:
+        kwargs = {}
         if settings.css:
-            kwargs = {'css': settings.css}
-        else:
-            kwargs = {}
+            kwargs['css'] = settings.css
+        if settings.textclass:
+            kwargs['textclass'] = settings.textclass
         transform(settings.xsltfilename, inputfilename, outputfilename, settings.encoding, **kwargs)
     except Exception as e:
         if settings.ignoreerrors:
@@ -78,7 +81,7 @@ def process(inputfilename, outputfilename=None):
 
 def main(xsltfilename, outputextension, usagetext):
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "o:E:hrqs:", ["help"])
+        opts, args = getopt.getopt(sys.argv[1:], "o:E:hrqs:t:", ["help"])
     except getopt.GetoptError as err:
         print(str(err), file=sys.stderr)
         usage()
@@ -109,6 +112,8 @@ def main(xsltfilename, outputextension, usagetext):
             settings.ignoreerrors = True
         elif o == '-s':
             settings.css = a
+        elif o == '-t':
+            settings.textclass = a
         else:
             raise Exception("No such option: " + o)
 

setup.py

@@ -11,7 +11,7 @@ def read(fname):
 
 setup(
     name = "FoLiA-tools",
-    version = "2.4.7", #also change in __init__.py
+    version = "2.4.8", #also change in __init__.py
     author = "Maarten van Gompel",
     author_email = "proycon@anaproy.nl",
     description = ("FoLiA-tools contains various Python-based command line tools for working with FoLiA XML (Format for Linguistic Annotation)"),