Oniloinsigh
/
stor-toolchain


			
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750
							import io
import unittest
import xml.etree.ElementTree as ET

from toolchain.parsers.parsing_error import ParsingError
from toolchain.parsers.xliff_parser import Xliff12Parser, Xliff20Parser

class TestXliff12Parser(unittest.TestCase):

    LANGUAGE_CODE_SRC = "en"
    LANGUAGE_CODE_TGT = "ga"

    ROOT_TEMPLATE = \
        "<xliff xmlns=\"urn:oasis:names:tc:xliff:document:1.2\" version=\"1.2\">\
            <file original=\"/path/to/original\" source-language=\"{0}\" target-language=\"{1}\" datatype=\"datatype\">\
                <header/>\
                <body>\
                {2}\
                </body>\
            </file>\
         </xliff>"

    def setUp(self):
        self.output_src = io.StringIO()
        self.output_tgt = io.StringIO()
        self.parser = Xliff12Parser(self.LANGUAGE_CODE_SRC, self.LANGUAGE_CODE_TGT)


    def tearDown(self):
        self.output_src.close()
        self.output_tgt.close()


    def make_document(self, source_language_code, target_language_code, content):
        return ET.fromstring(TestXliff12Parser.ROOT_TEMPLATE.format(source_language_code, target_language_code, content))


    def test_empty_body(self):
        document = self.make_document("en", "ga", "")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_absent_src(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <target>capall</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_absent_tgt(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>horse</source>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_empty_src(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source/>\
                <target>capall</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_empty_tgt(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>horse</source>\
                <target/>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_single_valid(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>horse</source>\
                <target>capall</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_language_variants(self):
        document = self.make_document("en-GB", "ga-IE", "\
            <trans-unit>\
                <source>horse</source>\
                <target>capall</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_languages_reversed(self):
        document = self.make_document("ga", "en", "\
            <trans-unit>\
                <source>capall</source>\
                <target>horse</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_inner_tags_all(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source><inner>yellow</inner></source>\
                <target><g>buí</g></target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "buí\n")


    def test_single_valid_inner_tags_start(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source><inner>ye</inner>llow</source>\
                <target><g>buí</g></target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "buí\n")


    def test_single_valid_inner_tags_all(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>yell<inner>ow</inner></source>\
                <target><g>buí</g></target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "buí\n")


    def test_single_valid_with_group(self):
        document = self.make_document("en", "ga", "\
            <group>\
                <trans-unit>\
                    <source>horse</source>\
                    <target>capall</target>\
                </trans-unit>\
            </group>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_multiple_group(self):
        document = self.make_document("en", "ga", "\
            <group>\
                <group>\
                    <trans-unit>\
                        <source>horse</source>\
                        <target>capall</target>\
                    </trans-unit>\
                </group>\
            </group>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_extra_whitespace_leading_trailing(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>yellow </source>\
                <target>    \tbuí</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow \n")
        self.assertEqual(self.output_tgt.getvalue(), "    \tbuí\n")


    def test_extra_whitespace_contained(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>cake</source>\
                <target>cáca    \tmilis</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "cake\n")
        self.assertEqual(self.output_tgt.getvalue(), "cáca    \tmilis\n")


    def test_newline_contained(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>cake</source>\
                <target>cáca\nmilis</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "cake\n")
        self.assertEqual(self.output_tgt.getvalue(), "cácamilis\n")


    def test_only_whitespace(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>yellow</source>\
                <target>   </target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "   \n")


    def test_only_newline(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>yellow</source>\
                <target>\n</target>\
            </trans-unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "\n")


    def test_multiple_valid(self):
        document = self.make_document("en", "ga", "\
            <trans-unit>\
                <source>horse</source>\
                <target>capall</target>\
            </trans-unit>\
            <group>\
                <trans-unit>\
                    <source>eat</source>\
                </trans-unit>\
            </group>\
            <group>\
                <group>\
                    <trans-unit>\
                        <source>yell<inner>ow</inner></source>\
                        <target><g>buí</g></target>\
                    </trans-unit>\
                </group>\
            </group>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\nyellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\nbuí\n")


    def test_no_target_language(self):
        document = ET.fromstring("\
            <xliff xmlns=\"urn:oasis:names:tc:xliff:document:1.2\" version=\"1.2\">\
                <file original=\"/path/to/original\" source-language=\"en\" datatype=\"datatype\">\
                    <header/>\
                    <body>\
                        <trans-unit>\
                            <source>horse</source>\
                            <target>capall</target>\
                        </trans-unit>\
                    </body>\
                </file>\
            </xliff>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_no_source_language(self):
        document = ET.fromstring("\
            <xliff xmlns=\"urn:oasis:names:tc:xliff:document:1.2\" version=\"1.2\">\
                <file original=\"/path/to/original\" target-language=\"ga\" datatype=\"datatype\">\
                    <header/>\
                    <body>\
                        <trans-unit>\
                            <source>horse</source>\
                            <target>capall</target>\
                        </trans-unit>\
                    </body>\
                </file>\
            </xliff>\
        ")

        with self.assertRaises(ParsingError):
            self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


class TestXliff20Parser(unittest.TestCase):

    LANGUAGE_CODE_SRC = "en"
    LANGUAGE_CODE_TGT = "ga"

    ROOT_TEMPLATE = \
        "<xliff xmlns=\"urn:oasis:names:tc:xliff:document:2.0\" version=\"2.0\" srcLang=\"{0}\" trgLang=\"{1}\">\
            <file>\
            {2}\
            </file>\
         </xliff>"

    def setUp(self):
        self.output_src = io.StringIO()
        self.output_tgt = io.StringIO()
        self.parser = Xliff20Parser(self.LANGUAGE_CODE_SRC, self.LANGUAGE_CODE_TGT)


    def tearDown(self):
        self.output_src.close()
        self.output_tgt.close()


    def make_document(self, source_language_code, target_language_code, content):
        return ET.fromstring(TestXliff20Parser.ROOT_TEMPLATE.format(source_language_code, target_language_code, content))


    def test_empty_body(self):
        document = self.make_document("en", "ga", "")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_absent_src(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <target>capall</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_absent_tgt(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>horse</source>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_empty_src(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source/>\
                    <target>capall</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_empty_tgt(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>horse</source>\
                    <target/>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_single_valid(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>horse</source>\
                    <target>capall</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_language_variants(self):
        document = self.make_document("en-GB", "ga-IE", "\
            <unit id=\"7\">\
                <segment>\
                    <source>horse</source>\
                    <target>capall</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_languages_reversed(self):
        document = self.make_document("ga", "en", "\
            <unit id=\"7\">\
                <segment>\
                    <source>capall</source>\
                    <target>horse</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_inner_tags_all(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source><inner>yellow</inner></source>\
                    <target><g>buí</g></target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "buí\n")


    def test_single_valid_inner_tags_start(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source><inner>ye</inner>llow</source>\
                    <target><g>buí</g></target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "buí\n")


    def test_single_valid_inner_tags_all(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>yell<inner>ow</inner></source>\
                    <target><g>buí</g></target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "buí\n")


    def test_single_valid_with_group(self):
        document = self.make_document("en", "ga", "\
            <group>\
                <unit id=\"7\">\
                    <segment>\
                        <source>horse</source>\
                        <target>capall</target>\
                    </segment>\
                </unit>\
            </group>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_single_valid_multiple_group(self):
        document = self.make_document("en", "ga", "\
            <group>\
                <group>\
                    <group>\
                        <unit id=\"7\">\
                            <segment>\
                                <source>horse</source>\
                                <target>capall</target>\
                            </segment>\
                        </unit>\
                    </group>\
                </group>\
            </group>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\n")


    def test_extra_whitespace_leading_trailing(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>yellow </source>\
                    <target>    \tbuí</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow \n")
        self.assertEqual(self.output_tgt.getvalue(), "    \tbuí\n")


    def test_extra_whitespace_contained(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>cake</source>\
                    <target>cáca    \tmilis</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "cake\n")
        self.assertEqual(self.output_tgt.getvalue(), "cáca    \tmilis\n")


    def test_newline_contained(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>cake</source>\
                    <target>cáca\nmilis</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "cake\n")
        self.assertEqual(self.output_tgt.getvalue(), "cácamilis\n")


    def test_only_whitespace(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>yellow</source>\
                    <target>   </target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "   \n")


    def test_only_newline(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>yellow</source>\
                    <target>\n</target>\
                </segment>\
            </unit>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "yellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "\n")


    def test_multiple_valid(self):
        document = self.make_document("en", "ga", "\
            <unit id=\"7\">\
                <segment>\
                    <source>horse</source>\
                    <target>capall</target>\
                </segment>\
            </unit>\
            <group>\
                <unit id=\"13\">\
                    <segment>\
                        <source>eat</source>\
                    </segment>\
                </unit>\
            </group>\
            <group>\
                <group>\
                    <group>\
                        <unit id=\"49\">\
                            <segment>\
                                <source>yell<inner>ow</inner></source>\
                                <target><g>buí</g></target>\
                            </segment>\
                        </unit>\
                    </group>\
                </group>\
            </group>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "horse\nyellow\n")
        self.assertEqual(self.output_tgt.getvalue(), "capall\nbuí\n")


    def test_no_target_language(self):
        document = ET.fromstring("\
            <xliff xmlns=\"urn:oasis:names:tc:xliff:document:2.0\" version=\"2.0\" srcLang=\"en\">\
                <file>\
                    <unit id=\"7\">\
                        <segment>\
                            <source>horse</source>\
                            <target>capall</target>\
                        </segment>\
                    </unit>\
                </file>\
            </xliff>\
        ")

        self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


    def test_no_source_language(self):
        document = ET.fromstring("\
            <xliff xmlns=\"urn:oasis:names:tc:xliff:document:2.0\" version=\"2.0\" trgLang=\"ga\">\
                <file>\
                    <unit id=\"7\">\
                        <segment>\
                            <source>horse</source>\
                            <target>capall</target>\
                        </segment>\
                    </unit>\
                </file>\
            </xliff>\
        ")

        with self.assertRaises(ParsingError):
            self.parser.parse_content(document, self.output_src, self.output_tgt)

        self.assertEqual(self.output_src.getvalue(), "")
        self.assertEqual(self.output_tgt.getvalue(), "")


if __name__ == "__main__":
    unittest.main()