Search in sources :

Example 1 with Cell

use of biblemulticonverter.schema.usx3.Cell in project BibleMultiConverter by schierlm.

the class USX3 method doImportBook.

@Override
protected ParatextBook doImportBook(File inputFile) throws Exception {
    if (!inputFile.getName().toLowerCase().endsWith(".usx"))
        return null;
    ValidateXML.validateFileBeforeParsing(getSchema(), inputFile);
    JAXBContext ctx = JAXBContext.newInstance(ObjectFactory.class.getPackage().getName());
    XMLInputFactory xif = XMLInputFactory.newFactory();
    XMLStreamReader xsr = xif.createXMLStreamReader(new FileInputStream(inputFile));
    Unmarshaller u = ctx.createUnmarshaller();
    u.setListener(unmarshallerLocationListener);
    unmarshallerLocationListener.setXMLStreamReader(inputFile.getName(), xsr);
    Usx doc = (Usx) u.unmarshal(xsr);
    xsr.close();
    ParatextBook.ParatextID id = ParatextBook.ParatextID.fromIdentifier(doc.getBook().getCode().toUpperCase());
    if (id == null) {
        System.out.println("WARNING: Skipping book with unknown ID: " + doc.getBook().getCode());
        return null;
    }
    ParatextBook result = new ParatextBook(id, doc.getBook().getContent());
    ParatextCharacterContent charContent = null;
    for (Object o : doc.getParaOrTableOrChapter()) {
        if (o instanceof Para) {
            Para para = (Para) o;
            if (BOOK_HEADER_ATTRIBUTE_TAGS.contains(para.getStyle().value())) {
                String value = "";
                for (Object oo : para.getContent()) {
                    if (oo instanceof String) {
                        value += ((String) oo).replaceAll("[ \r\n\t]+", " ");
                    } else {
                        throw new RuntimeException("Unsupported content in attribute: " + oo.getClass());
                    }
                }
                result.getAttributes().put(para.getStyle().value(), value);
                charContent = null;
            } else if (para.getStyle() == ParaStyle.PB) {
                if (charContent == null) {
                    charContent = new ParatextCharacterContent();
                    result.getContent().add(charContent);
                }
                charContent.getContent().add(new ParatextCharacterContent.AutoClosingFormatting(ParatextCharacterContent.AutoClosingFormattingKind.PAGE_BREAK, false));
            } else if (PARA_STYLE_UNSUPPORTED.contains(para.getStyle())) {
                // skip
                charContent = null;
            } else {
                result.getContent().add(new ParatextBook.ParagraphStart(PARA_STYLE_MAP.get(para.getStyle())));
                charContent = null;
                if (!para.getContent().isEmpty()) {
                    charContent = new ParatextCharacterContent();
                    result.getContent().add(charContent);
                    parseCharContent(para.getContent(), charContent);
                }
            }
        } else if (o instanceof Table) {
            Table table = (Table) o;
            for (Row row : table.getRow()) {
                result.getContent().add(new ParatextBook.ParagraphStart(ParatextBook.ParagraphKind.TABLE_ROW));
                for (Object oo : row.getVerseOrCell()) {
                    if (oo instanceof Verse) {
                        Verse verse = (Verse) oo;
                        ParatextCharacterContent.ParatextCharacterContentPart verseStartOrEnd = handleVerse(verse);
                        charContent = new ParatextCharacterContent();
                        result.getContent().add(charContent);
                        charContent.getContent().add(verseStartOrEnd);
                    } else if (oo instanceof Cell) {
                        Cell cell = (Cell) oo;
                        result.getContent().add(new ParatextBook.TableCellStart(cell.getStyle().value()));
                        charContent = new ParatextCharacterContent();
                        result.getContent().add(charContent);
                        parseCharContent(cell.getContent(), charContent);
                    } else {
                        throw new IOException("Unsupported table row element: " + o.getClass().getName());
                    }
                }
            }
            charContent = null;
        } else if (o instanceof Chapter) {
            Chapter chapter = (Chapter) o;
            if (chapter.getSid() != null) {
                // Assume start chapter
                result.getContent().add(new ParatextBook.ChapterStart(new ChapterIdentifier(result.getId(), ((Chapter) o).getNumber().intValue())));
            } else if (chapter.getEid() != null) {
                // Assume end chapter
                ChapterIdentifier location = ChapterIdentifier.fromLocationString(chapter.getEid());
                if (location == null) {
                    throw new IOException("Invalid chapter eid found: " + chapter.getEid());
                }
                result.getContent().add(new ParatextBook.ChapterEnd(location));
            } else {
                throw new IOException("Invalid chapter found, both sid and eid are undefined: " + chapter);
            }
            charContent = null;
        } else if (o instanceof Note) {
            if (charContent == null) {
                charContent = new ParatextCharacterContent();
                result.getContent().add(charContent);
            }
            Note note = (Note) o;
            ParatextCharacterContent.FootnoteXref nx = new ParatextCharacterContent.FootnoteXref(NOTE_STYLE_MAP.get(note.getStyle()), note.getCaller());
            charContent.getContent().add(nx);
            parseCharContent(note.getContent(), nx);
        } else if (o instanceof Sidebar) {
            System.out.println("WARNING: Skipping sidebar (study bible content)");
            charContent = null;
        } else {
            throw new IOException("Unsupported book level element: " + o.getClass().getName());
        }
    }
    return result;
}
Also used : XMLStreamReader(javax.xml.stream.XMLStreamReader) JAXBContext(javax.xml.bind.JAXBContext) Unmarshaller(javax.xml.bind.Unmarshaller) Cell(biblemulticonverter.schema.usx3.Cell) Table(biblemulticonverter.schema.usx3.Table) Para(biblemulticonverter.schema.usx3.Para) Chapter(biblemulticonverter.schema.usx3.Chapter) IOException(java.io.IOException) FileInputStream(java.io.FileInputStream) Note(biblemulticonverter.schema.usx3.Note) Usx(biblemulticonverter.schema.usx3.Usx) Row(biblemulticonverter.schema.usx3.Row) ChapterIdentifier(biblemulticonverter.format.paratext.model.ChapterIdentifier) XMLInputFactory(javax.xml.stream.XMLInputFactory) Verse(biblemulticonverter.schema.usx3.Verse) Sidebar(biblemulticonverter.schema.usx3.Sidebar)

Example 2 with Cell

use of biblemulticonverter.schema.usx3.Cell in project BibleMultiConverter by schierlm.

the class USX3 method doExportBook.

@Override
protected void doExportBook(ParatextBook book, File outFile) throws Exception {
    ObjectFactory of = new ObjectFactory();
    Usx usx = of.createUsx();
    usx.setVersion("3.0");
    usx.setBook(of.createBook());
    usx.getBook().setStyle("id");
    usx.getBook().setCode(book.getId().getIdentifier());
    usx.getBook().setContent(book.getBibleName());
    for (Map.Entry<String, String> attr : book.getAttributes().entrySet()) {
        Para para = new Para();
        para.setStyle(ParaStyle.fromValue(attr.getKey()));
        para.getContent().add(attr.getValue());
        usx.getParaOrTableOrChapter().add(para);
    }
    book.accept(new ParatextBook.ParatextBookContentVisitor<IOException>() {

        List<Object> currentContent = null;

        Table currentTable = null;

        @Override
        public void visitChapterStart(ChapterIdentifier location) throws IOException {
            Chapter ch = new Chapter();
            ch.setStyle("c");
            ch.setSid(location.toString());
            ch.setNumber(BigInteger.valueOf(location.chapter));
            usx.getParaOrTableOrChapter().add(ch);
            currentContent = null;
            currentTable = null;
        }

        @Override
        public void visitChapterEnd(ChapterIdentifier location) throws IOException {
            Chapter ch = new Chapter();
            ch.setEid(location.toString());
            usx.getParaOrTableOrChapter().add(ch);
            currentContent = null;
            currentTable = null;
        }

        @Override
        public void visitParagraphStart(ParatextBook.ParagraphKind kind) throws IOException {
            if (kind == ParatextBook.ParagraphKind.TABLE_ROW) {
                if (currentTable == null) {
                    currentTable = new Table();
                    usx.getParaOrTableOrChapter().add(currentTable);
                }
                Row row = new Row();
                row.setStyle("tr");
                currentTable.getRow().add(row);
                currentContent = currentTable.getRow().get(currentTable.getRow().size() - 1).getVerseOrCell();
            } else {
                Para para = new Para();
                para.setStyle(PARA_KIND_MAP.get(kind));
                usx.getParaOrTableOrChapter().add(para);
                currentContent = para.getContent();
                currentTable = null;
            }
        }

        @Override
        public void visitTableCellStart(String tag) throws IOException {
            if (currentTable == null) {
                System.out.println("WARNING: Table cell outside of table");
                return;
            }
            Row currentRow = currentTable.getRow().get(currentTable.getRow().size() - 1);
            Cell cell = new Cell();
            cell.setAlign(tag.contains("r") ? CellAlign.END : CellAlign.START);
            cell.setStyle(CellStyle.fromValue(tag));
            currentRow.getVerseOrCell().add(cell);
            currentContent = cell.getContent();
        }

        @Override
        public void visitParatextCharacterContent(ParatextCharacterContent content) throws IOException {
            if (currentContent == null)
                visitParagraphStart(ParatextBook.ParagraphKind.PARAGRAPH_P);
            content.accept(new USX3.USXCharacterContentVisitor(currentContent));
        }
    });
    JAXBContext ctx = JAXBContext.newInstance(ObjectFactory.class.getPackage().getName());
    Marshaller m = ctx.createMarshaller();
    if (!Boolean.getBoolean("biblemulticonverter.skipxmlvalidation"))
        m.setSchema(getSchema());
    m.marshal(usx, new UnifiedScriptureXMLWriter(new FileWriter(outFile), "UTF-8"));
}
Also used : Marshaller(javax.xml.bind.Marshaller) Table(biblemulticonverter.schema.usx3.Table) Para(biblemulticonverter.schema.usx3.Para) UnifiedScriptureXMLWriter(biblemulticonverter.format.paratext.utilities.UnifiedScriptureXMLWriter) FileWriter(java.io.FileWriter) Chapter(biblemulticonverter.schema.usx3.Chapter) JAXBContext(javax.xml.bind.JAXBContext) IOException(java.io.IOException) ObjectFactory(biblemulticonverter.schema.usx3.ObjectFactory) Usx(biblemulticonverter.schema.usx3.Usx) Row(biblemulticonverter.schema.usx3.Row) ChapterIdentifier(biblemulticonverter.format.paratext.model.ChapterIdentifier) Map(java.util.Map) EnumMap(java.util.EnumMap) Cell(biblemulticonverter.schema.usx3.Cell)

Example 3 with Cell

use of biblemulticonverter.schema.usx3.Cell in project simple-bigtable by spotify.

the class CellReadImplTest method testParentDataTypeToDataType.

@Test
public void testParentDataTypeToDataType() throws Exception {
    assertEquals(Optional.empty(), cellRead.parentTypeToCurrentType().apply(Collections.emptyList()));
    final Cell cell = Cell.getDefaultInstance();
    assertEquals(Optional.of(cell), cellRead.parentTypeToCurrentType().apply(Collections.singletonList(cell)));
}
Also used : Cell(com.google.bigtable.v2.Cell) Test(org.junit.Test)

Example 4 with Cell

use of biblemulticonverter.schema.usx3.Cell in project beam by apache.

the class BigtableTableTestUtils method setFixedTimestamp.

// There is no possibility to insert a value with fixed timestamp so we have to replace it
// for the testing purpose.
static com.google.bigtable.v2.Row setFixedTimestamp(com.google.bigtable.v2.Row row) {
    Family family = row.getFamilies(0);
    List<Column> columnsReplaced = family.getColumnsList().stream().map(column -> {
        Cell cell = column.getCells(0);
        return column(column.getQualifier().toStringUtf8(), cell.getValue().toByteArray());
    }).collect(toList());
    Family familyReplaced = Family.newBuilder().setName(family.getName()).addAllColumns(columnsReplaced).build();
    return com.google.bigtable.v2.Row.newBuilder().setKey(row.getKey()).addFamilies(familyReplaced).build();
}
Also used : BigtableUtils.byteStringUtf8(org.apache.beam.sdk.io.gcp.testing.BigtableUtils.byteStringUtf8) BigtableUtils.doubleToByteArray(org.apache.beam.sdk.io.gcp.testing.BigtableUtils.doubleToByteArray) UTF_8(java.nio.charset.StandardCharsets.UTF_8) Cell(com.google.bigtable.v2.Cell) Longs(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.primitives.Longs) Family(com.google.bigtable.v2.Family) Column(com.google.bigtable.v2.Column) LABELS(org.apache.beam.sdk.io.gcp.bigtable.RowUtils.LABELS) Schema(org.apache.beam.sdk.schemas.Schema) BigtableUtils.booleanToByteArray(org.apache.beam.sdk.io.gcp.testing.BigtableUtils.booleanToByteArray) Collectors.toList(java.util.stream.Collectors.toList) List(java.util.List) KEY(org.apache.beam.sdk.io.gcp.bigtable.RowUtils.KEY) BigtableUtils.longToByteArray(org.apache.beam.sdk.io.gcp.testing.BigtableUtils.longToByteArray) ImmutableList(org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList) Assert.fail(org.junit.Assert.fail) MatcherAssert.assertThat(org.hamcrest.MatcherAssert.assertThat) Row(org.apache.beam.sdk.values.Row) Matchers.containsString(org.hamcrest.Matchers.containsString) TIMESTAMP_MICROS(org.apache.beam.sdk.io.gcp.bigtable.RowUtils.TIMESTAMP_MICROS) VALUE(org.apache.beam.sdk.io.gcp.bigtable.RowUtils.VALUE) Nullable(org.checkerframework.checker.nullness.qual.Nullable) BigtableUtils.byteString(org.apache.beam.sdk.io.gcp.testing.BigtableUtils.byteString) Column(com.google.bigtable.v2.Column) Family(com.google.bigtable.v2.Family) Cell(com.google.bigtable.v2.Cell)

Example 5 with Cell

use of biblemulticonverter.schema.usx3.Cell in project simple-bigtable by spotify.

the class CellsReadImplTest method testParentDataTypeToDataType.

@Test
public void testParentDataTypeToDataType() throws Exception {
    assertEquals(Lists.newArrayList(), cellsRead.parentTypeToCurrentType().apply(Optional.empty()));
    assertEquals(Lists.newArrayList(), cellsRead.parentTypeToCurrentType().apply(Optional.of(Column.getDefaultInstance())));
    final Cell cell = Cell.getDefaultInstance();
    final Column column = Column.newBuilder().addCells(cell).build();
    assertEquals(ImmutableList.of(cell), cellsRead.parentTypeToCurrentType().apply(Optional.of(column)));
}
Also used : Column(com.google.bigtable.v2.Column) Cell(com.google.bigtable.v2.Cell) Test(org.junit.Test)

Aggregations

Cell (com.google.bigtable.v2.Cell)3 ChapterIdentifier (biblemulticonverter.format.paratext.model.ChapterIdentifier)2 Cell (biblemulticonverter.schema.usx3.Cell)2 Chapter (biblemulticonverter.schema.usx3.Chapter)2 Para (biblemulticonverter.schema.usx3.Para)2 Row (biblemulticonverter.schema.usx3.Row)2 Table (biblemulticonverter.schema.usx3.Table)2 Usx (biblemulticonverter.schema.usx3.Usx)2 Column (com.google.bigtable.v2.Column)2 IOException (java.io.IOException)2 JAXBContext (javax.xml.bind.JAXBContext)2 UnifiedScriptureXMLWriter (biblemulticonverter.format.paratext.utilities.UnifiedScriptureXMLWriter)1 Note (biblemulticonverter.schema.usx3.Note)1 ObjectFactory (biblemulticonverter.schema.usx3.ObjectFactory)1 Sidebar (biblemulticonverter.schema.usx3.Sidebar)1 Verse (biblemulticonverter.schema.usx3.Verse)1 Family (com.google.bigtable.v2.Family)1 FileInputStream (java.io.FileInputStream)1 FileWriter (java.io.FileWriter)1 UTF_8 (java.nio.charset.StandardCharsets.UTF_8)1