Minor additions.

* few German translations * help output for some tools.
jhellingman · Jul 29, 2024 · 1b81e91 · 1b81e91
1 parent 720f186
commit 1b81e91
Show file tree

Hide file tree

Showing 5 changed files with 76 additions and 13 deletions.
diff --git a/locale/messages.xml b/locale/messages.xml
@@ -888,6 +888,17 @@
 
     <msg:messages xml:lang="de" name="German">
 
+        <msg:message name="msgCountCorrectionsAppliedToText" plural="zero">Es wurden keine Korrekturen am Text vorgenommen.</msg:message>
+        <msg:message name="msgCountCorrectionsAppliedToText" plural="one">Die folgende Korrektur wurde am Text vorgenommen:</msg:message>
+        <msg:message name="msgCountCorrectionsAppliedToText">Die folgenden <msg:param name="count" type="integer"/> Korrekturen wurden am Text vorgenommen:</msg:message>
+
+        <msg:message name="msgCorrectionsNotAppliedToText">Die folgenden möglichen Korrekturen wurden nicht vorgenommen.</msg:message>
+        <msg:message name="msgQuestionablesOverview">Übersicht der möglichen Korrekturen.</msg:message>
+        <msg:message name="msgSuggestedCorrection">Vorgeschlagene Korrektur</msg:message>
+
+        <msg:message name="msgDramatisPersonae">Dramatis personae.</msg:message>
+        <msg:message name="msgUnidentifiedSpeaker">Unbekannter Sprecher.</msg:message>
+
         <msg:message name="msgGutenbergNoExternalReferences">Project Gutenberg verwendet keine aktiven externen Links in seinen E-Books.</msg:message>
         <msg:message name="msgGutenbergExternalReferencesExplanation">Die folgenden URLs dienen rein zur Information. Bei Bedarf können Sie sie in die Adressleiste Ihres Browsers kopieren.</msg:message>
         <msg:message name="msgIllustrator">Illustrator</msg:message>
@@ -909,6 +920,9 @@
         <msg:message name="msgReturnToNoteMarkInText">Zurück zur Note <msg:param name="mark"/> im Text.</msg:message>
 
         <msg:message name="msgPassim">Passim</msg:message>
+
+        <msg:message name="msgCountOccurrences" plural="zero">keine Fälle</msg:message>
+        <msg:message name="msgCountOccurrences" plural="one">ein Fall</msg:message>
         <msg:message name="msgCountOccurrences"><msg:param name="count"/> Fälle</msg:message>
         <msg:message name="msgContributor">Beiträger</msg:message>
 
@@ -968,7 +982,6 @@
         <msg:message name="msgCorrection">Korrektur</msg:message>
         <msg:message name="msgCorrections">Korrekturen</msg:message>
         <msg:message name="msgCorrectionsAppliedToText">Die folgenden Korrekturen sind am Text angewendet worden:</msg:message>
-        <msg:message name="msgCountCorrectionsAppliedToText">Die folgenden <msg:param name="count"/> Korrekturen sind am Text angewendet worden:</msg:message>
         <msg:message name="msgCorrectionsOverview">Übersicht der Korrekturen im Text</msg:message>
         <msg:message name="msgCover">Umslag</msg:message>
         <msg:message name="msgCoverImage">Titelbild</msg:message>

diff --git a/locale/messages.xsl b/locale/messages.xsl
@@ -20,7 +20,7 @@
     </xd:doc>
 
     <xsl:param name="srclang" select="'en'"/>
-    <xsl:param name="destlang" select="'nl'"/>
+    <xsl:param name="destlang" select="'de'"/>
 
     <xsl:strip-space elements="*"/>
 

diff --git a/modules/colophon.xsl b/modules/colophon.xsl
@@ -74,7 +74,7 @@
         <h3 class="main"><xsl:value-of select="f:message('msgAvailability')"/></h3>
         <xsl:apply-templates select="/*[self::TEI.2 or self::TEI]/teiHeader/fileDesc/publicationStmt/availability"/>
 
-        <xsl:if test="//figure[@id = 'cover-image'][f:rend-value(@rend, 'image') = 'images/new-cover.jpg']">
+        <xsl:if test="f:is-set('pg.compliant') and //figure[@id = 'cover-image'][f:rend-value(@rend, 'image') = 'images/new-cover.jpg']">
             <p>
                 <xsl:value-of select="f:message('msgPGCoverArtDedication')"/>
             </p>
@@ -1044,8 +1044,8 @@
         <div class="transcriberNote">
             <h2 class="main"><xsl:value-of select="f:message('msgOverviewForeignFragments')"/></h2>
 
-            <xsl:variable name="mainlang" select="/*[self::TEI.2 or self::TEI]/@lang"/>
-            <xsl:for-each-group select="//*[@lang != $mainlang]" group-by="@lang">
+            <xsl:variable name="mainLanguage" select="/*[self::TEI.2 or self::TEI]/@lang"/>
+            <xsl:for-each-group select="//*[@lang != $mainLanguage]" group-by="@lang">
                 <xsl:sort select="@lang"/>
                 <xsl:variable name="lang" select="@lang"/>
                 <h3 class="main"><xsl:value-of select="f:message($lang)"/></h3>

diff --git a/tools/extractPdf.pl b/tools/extractPdf.pl
@@ -14,12 +14,28 @@
 my $pdfcount = 1000;
 my $resolutionDpi = 300;
 my $extractActualImages = 0;
+my $showHelp = 0;
 
 GetOptions(
     'j' => \$extractActualImages,
-    'r=i' => \$resolutionDpi
+    'r=i' => \$resolutionDpi,
+    'q' => \$showHelp,
+    'help' => \$showHelp
     );
 
+
+if ($showHelp == 1) {
+    print "extractPdf.pl -- Wrapper around pdfimages.exe to extract images from a PDF file.\n\n";
+    print "Usage: extractPdf.pl [-jq] [-r=i] <file>\n\n";
+    print "Options:\n";
+    print "    j         Extract actual embedded images.\n";
+    print "    r=i       Output resolution in DPI.\n";
+    print "    q         Print this help and exit.\n";
+
+    exit(0);
+}
+
+
 sub list_recursively($);
 
 sub list_recursively($) {

diff --git a/tools/pgprepare.pl b/tools/pgprepare.pl
@@ -1,16 +1,38 @@
-# pgprepare.pl -- prepare a directory of text files for PGDP.
+# pgprepare.pl -- prepare a set of text files for upload to PGDP.
 
 use strict;
 use warnings;
 
 use Getopt::Long;
 use File::Copy;
 
+my $readUnicode = 0;
+my $showHelp = 0;
+my $verbose = 0;
+
+GetOptions(
+    'u' => \$readUnicode,
+    'v' => \$verbose,
+    'q' => \$showHelp,
+    'help' => \$showHelp);
+
+if ($showHelp == 1) {
+    print "pgprepare.pl -- PGDP pre-processor: prepare a set of text files for upload to PGDP.\n\n";
+    print "Usage: pgprepare.pl [-uq] <file>\n\n";
+    print "Options:\n";
+    print "    u         Read input files as unicode.\n";
+    print "    v         Verbose output to STDERR.\n";
+    print "    q         Print this help and exit.\n";
+
+    exit(0);
+}
+
 my $directory = '.';
 if (defined $ARGV[0]) {
     $directory = $ARGV[0];
 }
 
+
 listRecursively($directory);
 
 #
@@ -44,7 +66,14 @@ sub listRecursively {
 sub cleanText($) {
     my $textFile = shift;
 
-    open(INPUTFILE, $textFile) || die("Could not open file $textFile for reading.");
+    # open(INPUTFILE, $textFile) || die("Could not open file $textFile for reading.");
+    if ($readUnicode == 1) {
+        open(INPUTFILE, '<:encoding(UTF-8)', $textFile) || die("Could not open UTF-8 file $textFile for reading");
+        $verbose and print STDERR "Reading UTF-8 text file: $textFile\n";
+    } else {
+        open(INPUTFILE, $textFile) || die("Could not open file $textFile for reading");
+        $verbose and print STDERR "Reading text file: $textFile\n";
+    }
     open(OUTPUTFILE, "> $textFile.tmp") || die("Could not open $textFile.tmp for writing.");
     binmode(OUTPUTFILE, ":utf8");
 
@@ -62,10 +91,10 @@ ($)
         # Eliminate trailing spaces:
         $line =~ s/\s+$//;
 
-        # Handle Dutch low-opening quotes
-        $line =~ s/^[„]/"/g;
+        # Handle Dutch or German low-opening quotes
+        $line =~ s/^[\x{201E}]/"/g;
         $line =~ s/^,,([a-zA-Z])/"$1/g;
-        $line =~ s/ [„]/ "/g;
+        $line =~ s/ [\x{201E}]/ "/g;
         $line =~ s/ ,,([a-zA-Z])/ "$1/g;
 
         # Handle spacing around punctuation marks
@@ -77,10 +106,15 @@ ($)
 
         # Handle unwanted characters:
         $line =~ s/[•]/./g;
-        $line =~ s/[„]/"/g;
-        $line =~ s/[€]/E/g;
+        $line =~ s/[\x{201C}\x{201D}\x{201E}\x{201F}]/"/g;  # double quotation marks
+        $line =~ s/[\x{2018}\x{2019}\x{201A}\x{201B}]/'/g;  # single quotation marks
+        $line =~ s/[\x{20AC}]/E/g;                          # euro-sign
         $line =~ s/[™]/"/g;
 
+        $line =~ s/[\x{2E17}\x{2E40}]/-/g;                  # German double hyphen
+        $line =~ s/[\x{2014}]/--/g;                         # em-dash
+
+
         print OUTPUTFILE $line . "\n";
     }
     close(INPUTFILE);