Does anyone know of a Java library that will let me parse .PO files? I simply want to create a Map of IDs and Values so I can load them into a database.
I searched the Internet and couldn't find an existing library, either. If you use Scala, it's quite easy to write a parser yourself, thanks to its parser combinator feature.
Call PoParser.parsePo("po file content")
. The result is a list of Translation
.
I have made this code into a library (can be used by any JVM languages, including Java, of course!): https://github.com/ngocdaothanh/scaposer
import scala.util.parsing.combinator.JavaTokenParsers
trait Translation
case class SingularTranslation(
msgctxto: Option[String],
msgid: String,
msgstr: String) extends Translation
case class PluralTranslation(
msgctxto: Option[String],
msgid: String,
msgidPlural: String,
msgstrNs: Map[Int, String]) extends Translation
// http://www.gnu.org/software/hello/manual/gettext/PO-Files.html
object PoParser extends JavaTokenParsers {
// Removes the first and last quote (") character of strings
// and concats them.
private def unquoted(quoteds: List[String]): String =
quoteds.foldLeft("") { (acc, quoted) =>
acc + quoted.substring(1, quoted.length - 1)
}
// Scala regex is single line by default
private def comment = rep(regex("^#.*".r))
private def msgctxt = "msgctxt" ~ rep(stringLiteral) ^^ {
case _ ~ quoteds => unquoted(quoteds)
}
private def msgid = "msgid" ~ rep(stringLiteral) ^^ {
case _ ~ quoteds => unquoted(quoteds)
}
private def msgidPlural = "msgid_plural" ~ rep(stringLiteral) ^^ {
case _ ~ quoteds => unquoted(quoteds)
}
private def msgstr = "msgstr" ~ rep(stringLiteral) ^^ {
case _ ~ quoteds => unquoted(quoteds)
}
private def msgstrN = "msgstr[" ~ wholeNumber ~ "]" ~ rep(stringLiteral) ^^ {
case _ ~ number ~ _ ~ quoteds => (number.toInt, unquoted(quoteds))
}
private def singular =
(opt(comment) ~ opt(msgctxt) ~
opt(comment) ~ msgid ~
opt(comment) ~ msgstr ~ opt(comment)) ^^ {
case _ ~ ctxto ~ _ ~ id ~ _ ~ s ~ _ =>
SingularTranslation(ctxto, id, s)
}
private def plural =
(opt(comment) ~ opt(msgctxt) ~
opt(comment) ~ msgid ~
opt(comment) ~ msgidPlural ~
opt(comment) ~ rep(msgstrN) ~ opt(comment)) ^^ {
case _ ~ ctxto ~ _ ~ id ~ _ ~ idp ~ _ ~ tuple2s ~ _ =>
PluralTranslation(ctxto, id, idp, tuple2s.toMap)
}
private def exp = rep(singular | plural)
def parsePo(po: String): List[Translation] = {
val parseRet = parseAll(exp, po)
if (parseRet.successful) parseRet.get else Nil
}
}