Transifex integration (translation management)

.gitignore

@@ -1,6 +1,10 @@
 #########################
 #### GENERAL or ROOT ####
 #########################
+
+# Transifex
+.transifexrc
+
 # Maven
 target/
 

.tx/config

@@ -0,0 +1,39 @@
+[main]
+host = https://www.transifex.com
+minimum_perc = 50
+
+[epubcheck.ErrorsWarnings]
+file_filter = src/main/resources/com/adobe/epubcheck/messages/MessageBundle_<lang>.properties
+source_file = src/main/resources/com/adobe/epubcheck/messages/MessageBundle.properties
+source_lang = en
+type = UNICODEPROPERTIES
+
+[epubcheck.CommandlineMessages]
+file_filter = src/main/resources/com/adobe/epubcheck/util/messages_<lang>.properties
+source_file = src/main/resources/com/adobe/epubcheck/util/messages.properties
+source_lang = en
+type = UNICODEPROPERTIES
+
+[epubcheck.CssParser]
+file_filter = src/main/resources/org/idpf/epubcheck/util/css/messages_<lang>.properties
+source_file = src/main/resources/org/idpf/epubcheck/util/css/messages.properties
+source_lang = en
+type = UNICODEPROPERTIES
+
+[epubcheck.jing-xsd-validation]
+file_filter = src/main/resources/com/thaiopensource/datatype/xsd/resources/Messages_<lang>.properties
+source_file = src/main/resources/com/thaiopensource/datatype/xsd/resources/Messages.properties
+source_lang = en
+type = PROPERTIES
+
+[epubcheck.jing-relaxng-validation]
+file_filter = src/main/resources/com/thaiopensource/relaxng/pattern/resources/Messages_<lang>.properties
+source_file = src/main/resources/com/thaiopensource/relaxng/pattern/resources/Messages.properties
+source_lang = en
+type = PROPERTIES
+
+[epubcheck.jing-schematron-validation]
+file_filter = src/main/resources/com/thaiopensource/validate/schematron/resources/Messages_<lang>.properties
+source_file = src/main/resources/com/thaiopensource/validate/schematron/resources/Messages.properties
+source_lang = en
+type = PROPERTIES

pom.xml

@@ -233,6 +233,8 @@
                 <directory>src/main/resources</directory>
                 <excludes>
                     <exclude>com/adobe/epubcheck/schema/30/*.sch</exclude>
+                    <exclude>com/thaiopensource/relaxng/pattern/resources/Messages.properties</exclude>
+                    <exclude>com/thaiopensource/datatype/xsd/resources/Messages.properties</exclude>
                 </excludes>
             </resource>
             <resource>

src/build/transifex-pull.sh

@@ -0,0 +1,92 @@
+#!/bin/bash
+
+# bash script to update and normalize
+#  pulled transifex properties files
+# 
+# Author:  Tobias Fischer (https://github.com/tofi86)
+# Project: IDPF/EpubCheck (https://github.com/IDPF/epubcheck)
+# 
+# Date: 2015-10-09
+# License: MIT License
+# 
+
+param1=$1
+
+
+function escapeISO88591() {
+  file=$1
+  echo "- Escaping ISO-8859-1 encodings with Unicode escapes"
+  native2ascii -encoding ISO-8859-1 ${file} ${file}
+}
+
+function removeJavaEscapes() {
+  file=$1
+
+  # replace \\ -> \, \` -> `, \= -> =, \: -> :, \! -> !
+  sed -E -i -- 's/\\([\\`=:!])/\1/g' ${file}
+
+  # make unicode escapes \u00fc uppercase \u00FC
+  perl -i -pe 's/\\u([0-9a-f]{4})/\\u\U\1/g' ${file}
+
+  # replace newlines in help_text
+  sed -E -i -- '/^help_text/s/((\\n)+)/\1\\\'$'\n          /g' ${file}
+  sed -E -i -- 's/^(          )([[:space:]]+)/\1\\\2/g' ${file}
+
+  # remove temp file
+  rm ${file}-- 2> /dev/null
+}
+
+function processFile() {
+  file=$1
+
+  echo ""
+  echo "Processing file '${file}'"
+  file ${file} | grep 'ISO-8859' > /dev/null
+  if [ $? -eq 0 ]; then
+    escapeISO88591 ${file}
+  fi
+
+  removeJavaEscapes ${file}
+}
+
+
+# Check if this is running from repo root dir near the .tx/ folder
+if [ ! -d .tx/ ] ; then
+	echo "FATAL: You need to run this script from the repository's root directory!"
+	echo "e.g. ./src/build/transifex-pull.sh --all"
+	exit 1
+fi
+
+
+# Check for Transifex Commandline Client
+if [ `which tx >/dev/null ; echo $?` -eq 1 ] ; then
+	echo "FATAL: You need to install the Transifex Commandline Client first in order to run this script!"
+	echo "Instructions: http://docs.transifex.com/client/setup/"
+	exit 1
+fi
+
+
+# Show help if no language parameter is passed to the script or --help
+if [[ -z ${param1} || ${param1} == "--help" ]] ; then
+	echo "usage: transifex-pull.sh [--all | <2-digit-country-code>]"
+	echo "examples:"
+	echo "  transifex-pull.sh --all"
+	echo "  transifex-pull.sh de"
+
+# Pull ALL translations
+elif [ ${param1} == "--all" ] ; then
+	minimum_percent_translated=$(awk -F "=" '/minimum_perc/ {print $2}' .tx/config)
+	echo "Pulling ALL epubcheck translations (>${minimum_percent_translated}% done) from Transifex..."
+	echo ""
+	tx pull -f | tee /dev/stderr | grep "> [a-z][a-z]: " | awk '{print $3}' | while read f; do processFile ${f}; done
+
+# Pull translations for a 2-digit-language-code
+elif [ ${#param1} -eq 2 ] ; then
+	echo "Pulling epubcheck translation '${param1}' from Transifex..."
+	echo ""
+	tx pull -f -l ${param1} | tee /dev/stderr | grep "${param1}: " | awk '{print $3}' | while read f; do processFile ${f}; done
+
+else
+	echo "FATAL: Couldn't recognize language code '${param1}'. Exit."
+	exit 1
+fi

src/main/resources/com/thaiopensource/datatype/xsd/resources/Messages.properties

@@ -0,0 +1,61 @@
+# Properties file specifying messages
+enumeration_param=\"enumeration\" facet is not allowed as a parameter: use \"value\" element instead
+whiteSpace_param=\"whiteSpace\" facet is not allowed as a parameter
+unrecognized_param=unrecognized parameter \"{0}\"
+invalid_regex=invalid regular expression: {0}
+not_ordered=parameter can only be applied to ordered datatype
+invalid_limit=\"{0}\" is not allowed by the base type: {1}
+no_length=base datatype does not define a units of length
+scale_not_derived_from_decimal=\"scale\" parameter can only be applied to datatype derived from \"decimal\"
+scale_not_non_negative_integer=\"scale\" parameter must be non negative integer
+length_not_non_negative_integer=\"length\" parameter must be non negative integer
+precision_not_derived_from_decimal=\"precision\" parameter can only be applied to datatype derived from \"decimal\"
+precision_not_positive_integer=\"precision\" parameter must be positive integer
+regex_impl_not_found=cannot find regular expression implementation; use JDK 1.4 or add Xerces2 to your classpath
+regex_internal_error=internal error in regular expression for datatype {0}
+
+# validation errors
+length_violation=must be {0} with length equal to {1} (actual length was {2})
+max_length_violation=must be {0} with length at most {1} (actual length was {2})
+min_length_violation=must be {0} with length at least {1} (actual length was {2})
+min_inclusive_violation=must be {0} greater than or equal to {1}
+min_exclusive_violation=must be {0} greater than {1}
+max_inclusive_violation=must be {0} less than or equal to {1}
+max_exclusive_violation=must be {0} less than {1}
+pattern_violation=must be {0} matching the regular expression \"{1}\"
+entity_violation=must be a name declared in the DTD as an unparsed entity
+undeclared_prefix=must be a QName whose prefix, if any, is declared (prefix \"{0}\" is not declared)
+precision_violation=must be {0} with at most {1} significant digits (found {2} digits)
+precision_1_violation=must be {0} with exactly one significant digit (found {1} digits)
+# part of the point is to avoid ugly "digit(s)" in the error message
+scale_violation=must be a decimal number with at most {0} significant digits after the decimal point (found {1} digits)
+scale_0_violation=must be a decimal number without any significant digits after the decimal point
+scale_1_violation=must be a decimal number with at most one significant digit after the decimal point (found {0} digits)
+lexical_violation=must be {0}
+
+# fragments substituted in above
+lexical_space_string=a string
+lexical_space_uri=a URI
+lexical_space_boolean=a boolean
+lexical_space_decimal=a decimal number
+lexical_space_float=a floating-point number
+lexical_space_duration=a duration
+lexical_space_hex=a hexadecimal string
+lexical_space_base64=a base64 string
+lexical_space_integer=an integer
+lexical_space_name=an XML name
+lexical_space_ncname=an XML name without colons
+lexical_space_nmtoken=an XML NMTOKEN
+lexical_space_qname=an XML QName
+lexical_space_list=a whitespace-delimited list
+lexical_space_list_ncname=a list of XML names without colons
+lexical_space_list_nmtoken=a list of XML NMTOKENs
+lexical_space_date_y_m_d_time=an ISO date and time
+lexical_space_time=an ISO time
+lexical_space_date_y_m_d=an ISO date
+lexical_space_date_y_m=an ISO year and month
+lexical_space_date_y=a year
+lexical_space_date_m_d=an ISO month and day (of the form --MM-DD)
+lexical_space_date_m=an ISO month (of the form --MM)
+lexical_space_date_d=an ISO day of the month (of the form ---DD)
+lexical_space_language=an RFC 3066 language identifier