Examples with FormattedText biblemulticonverter.data.FormattedText used on opensource projects

Example 6 with FormattedText

use of biblemulticonverter.data.FormattedText in project BibleMultiConverter by schierlm.

the class StrongDictionary method doImport.

@Override
public Bible doImport(File inputFile) throws Exception {
    Bible result = new Bible("Strong's dictionary");
    MetadataBook mb = new MetadataBook();
    mb.setValue(MetadataBookKey.description, "Strong's dictionary compiled by BibleMultiConverter from public sources.");
    mb.setValue(MetadataBookKey.source, "https://github.com/openscriptures/HebrewLexicon/ and https://github.com/morphgnt/strongs-dictionary-xml/");
    mb.setValue(MetadataBookKey.rights, "Strong's Greek Dictionary is in the public domain. Strong's Hebrew Dictionary is provided as XML files by the Open Scriptures Hebrew Bible Project, which are licensed CC-BY-4.0.");
    mb.finished();
    result.getBooks().add(mb.getBook());
    DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();
    Document doc;
    try (InputStream in = new URL("https://raw.githubusercontent.com/morphgnt/strongs-dictionary-xml/master/strongsgreek.xml").openStream()) {
        doc = db.parse(in);
    }
    for (Node entryNode = doc.getDocumentElement().getLastChild().getFirstChild(); entryNode != null; entryNode = entryNode.getNextSibling()) {
        Element entry = (Element) entryNode;
        int number = Integer.parseInt(entry.getAttribute("strongs"));
        System.out.println("G" + number);
        Book bk = new Book("G" + number, BookID.DICTIONARY_ENTRY, "G" + number, "G" + number);
        FormattedText prolog = new FormattedText();
        bk.getChapters().add(new Chapter());
        bk.getChapters().get(0).setProlog(prolog);
        result.getBooks().add(bk);
        Visitor<RuntimeException> v = prolog.getAppendVisitor();
        for (Node childNode = entry.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
            if (childNode instanceof Text) {
                if (childNode.getTextContent().replaceAll("[ \r\n\t]+", " ").equals(" or ") && childNode.getNextSibling().getNodeName().equals("greek")) {
                    v.visitFormattingInstruction(FormattingInstructionKind.ITALIC).visitText("-or-");
                    v.visitLineBreak(LineBreakKind.PARAGRAPH);
                } else if (childNode.getTextContent().trim().length() > 0) {
                    visitAttribute(v, "Remark", childNode.getTextContent());
                }
                continue;
            }
            Element elem = (Element) childNode;
            switch(elem.getNodeName()) {
                case "strongs":
                    int compNumber = Integer.parseInt(elem.getTextContent());
                    if (compNumber != number)
                        throw new IOException(compNumber + " != " + number);
                    break;
                case "greek":
                    v.visitHeadline(1).visitText(elem.getAttribute("unicode"));
                    visitAttribute(v, "Transliteration", elem.getAttribute("translit"));
                    break;
                case "pronunciation":
                    visitAttribute(v, "Pronunciation", elem.getAttribute("strongs"));
                    break;
                case "strongs_derivation":
                    visitAttribute(v, "Strongs Derivation", parseGreekContent(elem));
                    break;
                case "strongs_def":
                    visitAttribute(v, "Strongs Definition", parseGreekContent(elem));
                    break;
                case "kjv_def":
                    visitAttribute(v, "KJV Definition", parseGreekContent(elem));
                    if (elem.getNextSibling() != null && !elem.getNextSibling().getNodeName().equals("see")) {
                        Element moreInfo = doc.createElement("more_info");
                        elem.getParentNode().insertBefore(moreInfo, elem.getNextSibling());
                        while (moreInfo.getNextSibling() != null) {
                            if (moreInfo.getNextSibling().getNodeName().equals("see"))
                                break;
                            moreInfo.appendChild(moreInfo.getNextSibling());
                        }
                        if (moreInfo.getTextContent().trim().isEmpty())
                            moreInfo.getParentNode().removeChild(moreInfo);
                    }
                    break;
                case "strongsref":
                    visitAttribute(v, "Reference", "[" + elem.getAttribute("language").substring(0, 1) + Integer.parseInt(elem.getAttribute("strongs")) + "]");
                case "more_info":
                    visitAttribute(v, "More Information", parseGreekContent(elem));
                    break;
                case "see":
                    visitAttribute(v, "See Also", "[" + elem.getAttribute("language").substring(0, 1) + Integer.parseInt(elem.getAttribute("strongs")) + "]");
                    break;
                default:
                    throw new IOException(elem.getNodeName());
            }
        }
        prolog.trimWhitespace();
        prolog.finished();
    }
    try (InputStream in = new URL("https://raw.githubusercontent.com/openscriptures/HebrewLexicon/master/HebrewStrong.xml").openStream()) {
        doc = db.parse(in);
    }
    for (Node entryNode = doc.getDocumentElement().getFirstChild(); entryNode != null; entryNode = entryNode.getNextSibling()) {
        if (entryNode instanceof Text) {
            if (!entryNode.getTextContent().trim().isEmpty()) {
                throw new IOException(entryNode.getTextContent());
            }
            continue;
        }
        Element entry = (Element) entryNode;
        String id = entry.getAttribute("id");
        System.out.println(id);
        Book bk = new Book(id, BookID.DICTIONARY_ENTRY, id, id);
        FormattedText prolog = new FormattedText();
        bk.getChapters().add(new Chapter());
        bk.getChapters().get(0).setProlog(prolog);
        result.getBooks().add(bk);
        Visitor<RuntimeException> v = prolog.getAppendVisitor();
        for (Node childNode = entry.getFirstChild(); childNode != null; childNode = childNode.getNextSibling()) {
            if (childNode instanceof Text) {
                if (!childNode.getTextContent().trim().isEmpty()) {
                    throw new IOException(childNode.getTextContent());
                }
                continue;
            }
            Element elem = (Element) childNode;
            switch(elem.getNodeName()) {
                case "w":
                    v.visitHeadline(1).visitText(elem.getTextContent());
                    visitAttribute(v, "Transliteration", elem.getAttribute("xlit"));
                    visitAttribute(v, "Pronunciation", elem.getAttribute("pron"));
                    if (elem.getAttribute("xml:lang").equals("heb")) {
                        visitAttribute(v, "Language", "Hebrew");
                    } else if (elem.getAttribute("xml:lang").equals("arc")) {
                        visitAttribute(v, "Language", "Aramaic");
                    } else if (elem.getAttribute("xml:lang").equals("x-pn")) {
                        visitAttribute(v, "Language", "Proper Noun");
                    } else {
                        throw new IOException(elem.getAttribute("xml:lang"));
                    }
                    visitAttribute(v, "Part of speech", elem.getAttribute("pos"));
                    break;
                case "source":
                    visitAttribute(v, "Source", parseHebrewContent(elem));
                    break;
                case "meaning":
                    visitAttribute(v, "Meaning", parseHebrewContent(elem));
                    break;
                case "usage":
                    visitAttribute(v, "Usage", parseHebrewContent(elem));
                    break;
                case "note":
                    // skip
                    break;
                default:
                    throw new IOException(elem.getNodeName());
            }
        }
        prolog.trimWhitespace();
        prolog.finished();
    }
    return result;
}

Example 7 with FormattedText

use of biblemulticonverter.data.FormattedText in project BibleMultiConverter by schierlm.

the class TheWord method parseLine.

private int parseLine(Visitor<RuntimeException> visitor, String line, int pos, String endTag) {
    Visitor<RuntimeException> garbageVisitor = new FormattedText().getAppendVisitor();
    while (pos < line.length()) {
        if (line.charAt(pos) != '<') {
            int endPos = line.indexOf('<', pos);
            if (endPos == -1)
                endPos = line.length();
            visitor.visitText(line.substring(pos, endPos).replaceAll("[\r\n\t ]+", " "));
            pos = endPos;
            continue;
        }
        if (endTag != null && line.startsWith(endTag, pos))
            break;
        if (pos + 2 < line.length() && line.charAt(pos + 2) == '>' && "bius".indexOf(line.charAt(pos + 1)) != -1) {
            String newEndTag = "</" + line.charAt(pos + 1) + ">";
            if (parseLine(garbageVisitor, line, pos + 3, newEndTag) != -1) {
                FormattingInstructionKind kind;
                switch(line.charAt(pos + 1)) {
                    case 'b':
                        kind = FormattingInstructionKind.BOLD;
                        break;
                    case 'i':
                        kind = FormattingInstructionKind.ITALIC;
                        break;
                    case 'u':
                        kind = FormattingInstructionKind.UNDERLINE;
                        break;
                    case 's':
                        kind = FormattingInstructionKind.STRIKE_THROUGH;
                        break;
                    default:
                        throw new RuntimeException("Cannot happen");
                }
                pos = parseLine(visitor.visitFormattingInstruction(kind), line, pos + 3, newEndTag);
                continue;
            }
        } else if (line.startsWith("<sub>", pos) || line.startsWith("<sup>", pos)) {
            String newEndTag = "</" + line.substring(pos + 1, pos + 5);
            if (parseLine(garbageVisitor, line, pos + 5, newEndTag) != -1) {
                FormattingInstructionKind kind = line.charAt(pos + 3) == 'p' ? FormattingInstructionKind.SUPERSCRIPT : FormattingInstructionKind.SUBSCRIPT;
                pos = parseLine(visitor.visitFormattingInstruction(kind), line, pos + 5, newEndTag);
                continue;
            }
        } else if (line.startsWith("<FR>", pos)) {
            if (parseLine(garbageVisitor, line, pos + 4, "<Fr>") != -1) {
                pos = parseLine(visitor.visitFormattingInstruction(FormattingInstructionKind.WORDS_OF_JESUS), line, pos + 4, "<Fr>");
                continue;
            }
        } else if (line.startsWith("<FO>", pos)) {
            if (parseLine(garbageVisitor, line, pos + 4, "<Fo>") != -1) {
                pos = parseLine(visitor.visitFormattingInstruction(FormattingInstructionKind.LINK), line, pos + 4, "<Fo>");
                continue;
            }
        } else if (line.startsWith("<font color=\"gray\">/</font>", pos)) {
            visitor.visitVerseSeparator();
            pos += 27;
            continue;
        } else if (line.startsWith("<CL>", pos)) {
            visitor.visitLineBreak(LineBreakKind.NEWLINE);
            pos += 4;
            continue;
        } else if (line.startsWith("<CM>", pos)) {
            visitor.visitLineBreak(LineBreakKind.PARAGRAPH);
            pos += 4;
            continue;
        } else if (line.startsWith("<CI><PI>", pos)) {
            visitor.visitLineBreak(LineBreakKind.NEWLINE_WITH_INDENT);
            pos += 8;
            continue;
        } else if (line.startsWith("<TS", pos) && pos + 3 < line.length()) {
            char next = line.charAt(pos + 3);
            int depth, len;
            if (next == '>') {
                depth = 1;
                len = 4;
            } else if (pos + 4 < line.length() && line.charAt(pos + 4) == '>' && next >= '1' && next <= '3') {
                depth = next - '0';
                len = 5;
            } else {
                depth = len = 0;
            }
            String end = "<Ts>", altEnd = len == 5 ? "<Ts" + next + ">" : "<Ts>";
            if (line.indexOf(altEnd, pos) != -1 && (line.indexOf(end, pos) == -1 || line.indexOf(altEnd, pos) < line.indexOf(end, pos)))
                end = altEnd;
            if (len > 0 && parseLine(garbageVisitor, line, pos + len, end) != -1) {
                pos = parseLine(visitor.visitHeadline(depth), line, pos + len, end);
                continue;
            }
        } else if (line.startsWith("<RF", pos)) {
            int closePos = line.indexOf('>', pos);
            if (parseLine(garbageVisitor, line, closePos + 1, "<Rf>") != -1) {
                pos = parseLine(visitor.visitFootnote(), line, closePos + 1, "<Rf>");
                continue;
            }
        } else if (line.startsWith("<FI>", pos)) {
            if (parseLine(garbageVisitor, line, pos + 4, "<Fi>") != -1) {
                pos = parseLine(visitor.visitFormattingInstruction(FormattingInstructionKind.ITALIC), line, pos + 4, "<Fi>");
                continue;
            }
        } else if (line.startsWith("<S%", pos)) {
            int closePos = line.indexOf('>', pos);
            if (parseLine(garbageVisitor, line, closePos + 1, "<s%>") != -1) {
                String[] strongs = line.substring(pos + 3, closePos).split("%");
                int[] strongNumbers = new int[strongs.length];
                try {
                    for (int i = 0; i < strongs.length; i++) {
                        strongNumbers[i] = Integer.parseInt(strongs[i]);
                    }
                    pos = parseLine(visitor.visitGrammarInformation(strongNumbers, null, null), line, closePos + 1, "<s%>");
                    continue;
                } catch (NumberFormatException ex) {
                // malformed Strongs tag
                }
            }
        } else if (line.startsWith("<XWG", pos) || line.startsWith("<XWH", pos)) {
            int closePos = line.indexOf('>', pos);
            try {
                int number = Integer.parseInt(line.substring(pos + 4, closePos));
                visitor.visitGrammarInformation(new int[] { number }, null, null);
                pos = closePos + 1;
                continue;
            } catch (NumberFormatException ex) {
                System.out.println("WARNING: Invalid Strong number in tag " + line.substring(pos, closePos + 1));
                warningCount++;
            }
        } else if (line.startsWith("<WT", pos)) {
        // TODO parse morph information
        } else if (line.startsWith("<RX", pos)) {
        // TODO parse cross references
        } else if (line.startsWith("<CI>", pos) || line.startsWith("<PF", pos) || line.startsWith("<PI", pos)) {
        // extra formatting not supported by BMC
        } else if (warningCount < 100) {
            System.out.println("WARNING: Skipping unknown tag " + line.substring(pos, Math.min(pos + 20, line.length())));
            warningCount++;
        }
        // the tag is not supported (yet), skip the first character
        visitor.visitText("<");
        pos++;
    }
    if (endTag != null) {
        if (line.startsWith(endTag, pos))
            pos += endTag.length();
        else
            pos = -1;
    }
    return pos;
}

Example 8 with FormattedText

use of biblemulticonverter.data.FormattedText in project BibleMultiConverter by schierlm.

the class ZefDic method createXMLBible.

protected Dictionary createXMLBible(Bible bible) throws Exception {
    final ObjectFactory of = new ObjectFactory();
    Dictionary doc = of.createDictionary();
    doc.setDicversion("1");
    doc.setRevision("1");
    doc.setRefbible("any");
    doc.setType(TEnumDicType.X_DICTIONARY);
    String title = null;
    if (bible.getName().matches("X_(DICTIONARY|COMMENTARY|STRONG|DAILY)@.*")) {
        String[] parts = bible.getName().split("@", 2);
        doc.setType(TEnumDicType.valueOf(parts[0]));
        doc.setRefbible(parts[1]);
    } else {
        title = bible.getName();
    }
    doc.setINFORMATION(of.createTINFORMATION());
    doc.getINFORMATION().getTitleOrCreatorOrDescription().add(new JAXBElement<String>(new QName("title"), String.class, title));
    MetadataBook metadata = bible.getMetadataBook();
    if (metadata != null) {
        for (String key : metadata.getKeys()) {
            String value = metadata.getValue(key);
            if (value.equals("-empty-"))
                value = "";
            if (key.equals(MetadataBookKey.version.toString())) {
                doc.setDicversion(value);
            } else if (key.equals(MetadataBookKey.revision.toString())) {
                doc.setRevision(value);
            } else if (Arrays.asList(INFORMATION_KEYS).contains(key)) {
                doc.getINFORMATION().getTitleOrCreatorOrDescription().add(new JAXBElement<String>(new QName(key), String.class, value));
            }
        }
    }
    for (Book bk : bible.getBooks()) {
        if (bk.getId().equals(BookID.METADATA))
            continue;
        if (!bk.getId().equals(BookID.DICTIONARY_ENTRY)) {
            System.out.println("WARNING: Unable to export book " + bk.getAbbr());
            continue;
        }
        final TItem item = of.createTItem();
        if (!bk.getLongName().equals(bk.getShortName())) {
            TItem itm = of.createTItem();
            itm.setId(bk.getShortName());
            appendTextElement(itm, "title", bk.getLongName());
            TParagraph para2 = of.createTParagraph();
            SeeType see = of.createSeeType();
            see.setContent(bk.getLongName());
            para2.getContent().add(new JAXBElement<SeeType>(new QName("see"), SeeType.class, see));
            itm.getContent().add(new JAXBElement<TParagraph>(new QName("description"), TParagraph.class, para2));
            doc.getItem().add(itm);
        }
        item.setId(bk.getLongName());
        doc.getItem().add(item);
        class ZefState {

            TParagraph para = of.createTParagraph();

            boolean eatParagraph = false;

            public void flushPara(TItem item) {
                item.getContent().add(new JAXBElement<TParagraph>(new QName("description"), TParagraph.class, para));
                para = of.createTParagraph();
            }
        }
        final ZefState state = new ZefState();
        FormattedText text = bk.getChapters().get(0).getProlog();
        class LevelVisitor implements Visitor<RuntimeException> {

            final List<Serializable> target;

            private LevelVisitor(ZefState state) {
                target = state.para.getContent();
            }

            private LevelVisitor(MyAnyType parent) {
                target = parent.getContent();
            }

            private LevelVisitor(TStyle parent) {
                target = parent.getContent();
            }

            @Override
            public int visitElementTypes(String elementTypes) throws RuntimeException {
                return 0;
            }

            @Override
            public Visitor<RuntimeException> visitHeadline(int depth) throws RuntimeException {
                System.out.println("WARNING: Nested headlines are not supported");
                return null;
            }

            @Override
            public void visitStart() throws RuntimeException {
            }

            @Override
            public void visitText(String text) throws RuntimeException {
                if (text.length() > 0)
                    target.add(text);
            }

            @Override
            public Visitor<RuntimeException> visitFootnote() throws RuntimeException {
                System.out.println("WARNING: footnotes are not supported");
                return null;
            }

            @Override
            public Visitor<RuntimeException> visitCrossReference(String bookAbbr, BookID book, int firstChapter, String firstVerse, int lastChapter, String lastVerse) throws RuntimeException {
                if (firstChapter != lastChapter || !firstVerse.equals(lastVerse))
                    System.out.println("WARNING: Cross references to verse ranges are not supported");
                BibLinkType b = of.createBibLinkType();
                b.setBn("" + book.getZefID());
                b.setCn1("" + firstChapter);
                b.setVn1(firstVerse);
                target.add(new JAXBElement<BibLinkType>(new QName("bib_link"), BibLinkType.class, b));
                return null;
            }

            @Override
            public Visitor<RuntimeException> visitFormattingInstruction(FormattingInstructionKind kind) throws RuntimeException {
                String tag;
                switch(kind) {
                    case BOLD:
                        tag = "strong";
                        break;
                    case ITALIC:
                        tag = "em";
                        break;
                    case SUPERSCRIPT:
                        tag = "sup";
                        break;
                    case SUBSCRIPT:
                        tag = "sub";
                        break;
                    default:
                        return visitCSSFormatting(kind.getCss());
                }
                MyAnyType mat = of.createMyAnyType();
                target.add(new JAXBElement<MyAnyType>(new QName(tag), MyAnyType.class, mat));
                return new LevelVisitor(mat);
            }

            @Override
            public Visitor<RuntimeException> visitCSSFormatting(String css) throws RuntimeException {
                TStyle style = of.createTStyle();
                style.setCss(css);
                target.add(of.createTStyleSTYLE(style));
                return new LevelVisitor(style);
            }

            @Override
            public void visitVerseSeparator() throws RuntimeException {
                System.out.println("WARNING: Verse separators are not supported");
            }

            @Override
            public void visitLineBreak(LineBreakKind kind) throws RuntimeException {
                System.out.println("WARNING: Nested line breaks are not supported");
            }

            @Override
            public Visitor<RuntimeException> visitGrammarInformation(int[] strongs, String[] rmac, int[] sourceIndices) throws RuntimeException {
                System.out.println("WARNING: Grammar information is not supported");
                return null;
            }

            @Override
            public Visitor<RuntimeException> visitDictionaryEntry(String dictionary, String entry) throws RuntimeException {
                if (dictionary.equals("reflink")) {
                    RefLinkType r = of.createRefLinkType();
                    r.setMscope(entry.substring(1).replace('-', ';'));
                    target.add(new JAXBElement<RefLinkType>(new QName("reflink"), RefLinkType.class, r));
                } else {
                    SeeType see = of.createSeeType();
                    see.setTarget(dictionary.equals("dict") ? "x-self" : dictionary);
                    see.setContent(entry);
                    target.add(new JAXBElement<SeeType>(new QName("see"), SeeType.class, see));
                }
                return null;
            }

            @Override
            public void visitRawHTML(RawHTMLMode mode, String raw) throws RuntimeException {
                System.out.println("WARNING: Raw html output not supported");
            }

            @Override
            public Visitor<RuntimeException> visitVariationText(String[] variations) throws RuntimeException {
                throw new IllegalStateException("Variations not supported");
            }

            @Override
            public Visitor<RuntimeException> visitExtraAttribute(ExtraAttributePriority prio, String category, String key, String value) throws RuntimeException {
                return prio.handleVisitor(category, this);
            }

            @Override
            public boolean visitEnd() throws RuntimeException {
                return false;
            }
        }
        ;
        text.accept(new Visitor<RuntimeException>() {

            @Override
            public int visitElementTypes(String elementTypes) throws RuntimeException {
                return 0;
            }

            @Override
            public Visitor<RuntimeException> visitHeadline(int depth) throws RuntimeException {
                MyAnyType mat = of.createMyAnyType();
                JAXBElement<MyAnyType> elem = new JAXBElement<>(new QName("title"), MyAnyType.class, mat);
                if (depth == 1) {
                    state.flushPara(item);
                    item.getContent().add(elem);
                } else {
                    state.para.getContent().add(elem);
                }
                return new LevelVisitor(mat);
            }

            @Override
            public void visitStart() throws RuntimeException {
            }

            @Override
            public void visitText(String text) throws RuntimeException {
                new LevelVisitor(state).visitText(text);
            }

            @Override
            public Visitor<RuntimeException> visitFootnote() throws RuntimeException {
                System.out.println("WARNING: footnotes are not supported");
                return null;
            }

            @Override
            public Visitor<RuntimeException> visitCrossReference(String bookAbbr, BookID book, int firstChapter, String firstVerse, int lastChapter, String lastVerse) throws RuntimeException {
                return new LevelVisitor(state).visitCrossReference(bookAbbr, book, firstChapter, firstVerse, lastChapter, lastVerse);
            }

            @Override
            public Visitor<RuntimeException> visitFormattingInstruction(FormattingInstructionKind kind) throws RuntimeException {
                return new LevelVisitor(state).visitFormattingInstruction(kind);
            }

            @Override
            public Visitor<RuntimeException> visitCSSFormatting(String css) throws RuntimeException {
                return new LevelVisitor(state).visitCSSFormatting(css);
            }

            @Override
            public void visitVerseSeparator() throws RuntimeException {
                System.out.println("WARNING: Verse separators are not supported");
            }

            @Override
            public void visitLineBreak(LineBreakKind kind) throws RuntimeException {
                if (state.eatParagraph) {
                    state.eatParagraph = false;
                } else {
                    state.flushPara(item);
                    state.para = of.createTParagraph();
                }
            }

            @Override
            public Visitor<RuntimeException> visitGrammarInformation(int[] strongs, String[] rmac, int[] sourceIndices) throws RuntimeException {
                System.out.println("WARNING: Grammar information is not supported");
                return null;
            }

            @Override
            public Visitor<RuntimeException> visitDictionaryEntry(String dictionary, String entry) throws RuntimeException {
                return new LevelVisitor(state).visitDictionaryEntry(dictionary, entry);
            }

            @Override
            public void visitRawHTML(RawHTMLMode mode, String raw) throws RuntimeException {
                System.out.println("WARNING: Raw html output not supported");
            }

            @Override
            public Visitor<RuntimeException> visitVariationText(String[] variations) throws RuntimeException {
                throw new IllegalStateException("Variations not supported");
            }

            @Override
            public Visitor<RuntimeException> visitExtraAttribute(ExtraAttributePriority prio, String category, String key, String value) throws RuntimeException {
                if (prio == ExtraAttributePriority.KEEP_CONTENT && category.equals("zefdic")) {
                    // "zefdic", "field", "pronunciation");
                    return null;
                } else {
                    return prio.handleVisitor(category, this);
                }
            }

            @Override
            public boolean visitEnd() throws RuntimeException {
                return false;
            }
        });
        state.flushPara(item);
    }
    return doc;
}

Example 9 with FormattedText

use of biblemulticonverter.data.FormattedText in project BibleMultiConverter by schierlm.

the class ZefaniaXMLRoundtrip method parseBible.

protected Bible parseBible(XMLBIBLE doc) throws Exception {
    Bible result = new Bible(doc.getBiblename());
    MetadataBook metadata = new MetadataBook();
    if (doc.getStatus() != null) {
        metadata.setValue(MetadataBookKey.status, doc.getStatus().value());
    }
    if (doc.getVersion() != null) {
        metadata.setValue(MetadataBookKey.version, doc.getVersion());
    }
    if (doc.getRevision() != null) {
        metadata.setValue(MetadataBookKey.revision, doc.getRevision().toString());
    }
    for (JAXBElement<?> elem : doc.getINFORMATION().getTitleOrCreatorOrDescription()) {
        if (elem.getValue() == null)
            continue;
        String value = normalize(elem.getValue().toString(), true).trim();
        if (value.length() == 0)
            value = "-empty-";
        metadata.setValue(elem.getName().getLocalPart(), value);
    }
    metadata.finished();
    if (metadata.getKeys().size() > 0)
        result.getBooks().add(metadata.getBook());
    Set<String> abbrs = new HashSet<String>();
    Set<String> shortnames = new HashSet<String>();
    Map<BookID, String> abbrMap = new EnumMap<BookID, String>(BookID.class);
    List<BIBLEBOOK> nl = doc.getBIBLEBOOK();
    for (BIBLEBOOK e : nl) {
        String shortname = e.getBsname();
        int number = e.getBnumber().intValue();
        BookID bookID = BookID.fromZefId(number);
        if (shortname == null)
            shortname = "_" + bookID.getOsisID();
        else if (shortname.length() == 0)
            shortname = "_" + bookID.getOsisID() + "[[]]";
        String abbr = shortname.replaceAll("[^A-Z0-9a-zäöü]++", "");
        if (abbr.length() == 0 || Character.isLowerCase(abbr.charAt(0)))
            abbr = "X" + abbr;
        if (abbr.length() == 1)
            abbr += "x";
        if (abbrs.contains(abbr)) {
            for (int i = 2; i < 100; i++) {
                if (!abbrs.contains(abbr + i)) {
                    abbr = abbr + i;
                    break;
                }
            }
        }
        abbrs.add(abbr);
        abbrMap.put(bookID, abbr);
    }
    abbrs.clear();
    for (BIBLEBOOK e : nl) {
        String shortname = e.getBsname();
        String longname = e.getBname();
        int number = e.getBnumber().intValue();
        BookID bookID = BookID.fromZefId(number);
        if (shortname == null)
            shortname = "_" + bookID.getOsisID();
        else if (shortname.length() == 0)
            shortname = "_" + bookID.getOsisID() + "[[]]";
        if (longname == null)
            longname = "_" + bookID.getEnglishName();
        else if (longname.length() == 0)
            longname = "_" + bookID.getEnglishName() + "[[]]";
        else
            longname = longname.replaceAll("  ++", " ").trim();
        String abbr = shortname.replaceAll("[^A-Z0-9a-zäöü]++", "");
        if (abbr.length() == 0 || Character.isLowerCase(abbr.charAt(0)))
            abbr = "X" + abbr;
        if (abbr.length() == 1)
            abbr += "x";
        if (abbrs.contains(abbr)) {
            for (int i = 2; i < 100; i++) {
                if (!abbrs.contains(abbr + i)) {
                    abbr = abbr + i;
                    break;
                }
            }
        }
        abbrs.add(abbr);
        if (shortname.equals("Gen") && longname.equals("Genesis") && bookID == BookID.BOOK_Exod) {
            System.out.println("WARNING: Book number " + bookID.getZefID() + " has name " + longname);
            shortname = "Exo[[Gen]]";
            longname = "Exodus[[Genesis]]";
        }
        if (shortname.equals("1Chr") && longname.equals("2 Chronicles")) {
            System.out.println("WARNING: Book name 2 Chronicles has short name 1Chr");
            shortname = "2Chr[[1Chr]]";
        }
        if (shortnames.contains(shortname)) {
            System.out.println("WARNING: Duplicate short name " + shortname);
            for (int i = 2; i < 100; i++) {
                if (!shortnames.contains(shortname + i + "[[" + shortname + "]]")) {
                    shortname = shortname + i + "[[" + shortname + "]]";
                    break;
                }
            }
        }
        shortnames.add(shortname);
        Book book = new Book(abbr, bookID, shortname, longname);
        int lastvref = -1;
        List<Headline> headlineBuffer = new ArrayList<Headline>();
        for (CHAPTER e2 : e.getCHAPTER()) {
            int chapterNumber = e2.getCnumber().intValue();
            while (book.getChapters().size() < chapterNumber) book.getChapters().add(new Chapter());
            Chapter chapter = book.getChapters().get(chapterNumber - 1);
            for (Object e3 : e2.getPROLOGOrCAPTIONOrVERS()) {
                if (e3 instanceof CAPTION) {
                    CAPTION caption = (CAPTION) e3;
                    if (lastvref != -1 && lastvref != caption.getVref().intValue())
                        throw new IOException();
                    lastvref = caption.getVref().intValue();
                    int level;
                    if (caption.getType() == null) {
                        level = 9;
                    } else {
                        switch(caption.getType()) {
                            case X_H_1:
                                level = 1;
                                break;
                            case X_H_2:
                                level = 2;
                                break;
                            case X_H_3:
                                level = 3;
                                break;
                            case X_H_4:
                                level = 4;
                                break;
                            case X_H_5:
                                level = 5;
                                break;
                            case X_H_6:
                                level = 6;
                                break;
                            default:
                                throw new IOException();
                        }
                    }
                    Headline h = new Headline(level);
                    headlineBuffer.add(h);
                    if (!parseContent(h.getAppendVisitor(), caption.getContent(), abbrMap)) {
                        visitEmptyMarker(h.getAppendVisitor());
                    } else {
                        h.trimWhitespace();
                    }
                    h.finished();
                } else if (e3 instanceof REMARK) {
                    REMARK remark = (REMARK) e3;
                    int vref = remark.getVref().intValue();
                    int idx = chapter.getVerseIndex("" + vref);
                    if (idx == -1)
                        throw new IOException(vref + ":" + remark.getContent());
                    Verse v = chapter.getVerses().get(idx);
                    if (remark.getContent().size() != 1)
                        throw new IOException();
                    String remarkText = normalize((String) remark.getContent().get(0), true).trim();
                    v.getAppendVisitor().visitExtraAttribute(ExtraAttributePriority.KEEP_CONTENT, "zefania", "footnote-source", "remark").visitFootnote().visitText(remarkText);
                } else if (e3 instanceof XREF) {
                    XREF xref = (XREF) e3;
                    int vref = xref.getVref().intValue();
                    int idx = chapter.getVerseIndex("" + vref);
                    if (idx == -1)
                        throw new IOException(vref + ":" + xref.getMscope());
                    Verse v = chapter.getVerses().get(idx);
                    Visitor<RuntimeException> footnoteVisitor = v.getAppendVisitor().visitExtraAttribute(ExtraAttributePriority.KEEP_CONTENT, "zefania", "footnote-source", "outer-xref").visitFootnote();
                    boolean first = true;
                    for (String mscope : xref.getMscope().split(" ")) {
                        Matcher m = Utils.compilePattern("([0-9]+);([0-9]+)(-[0-9]+)?;([0-9]+)(-[0-9]+)?").matcher(mscope);
                        if (!m.matches())
                            throw new IOException(mscope);
                        BookID xrefBookID = BookID.fromZefId(Integer.parseInt(m.group(1)));
                        int xrefChapter = Integer.parseInt(m.group(2)), endChapter = xrefChapter;
                        if (m.group(3) != null)
                            endChapter = Integer.parseInt(m.group(3).substring(1));
                        String verse = m.group(4);
                        if (verse.equals("0"))
                            verse = "1//G";
                        String endVerse = m.group(5);
                        if (endVerse == null)
                            endVerse = verse;
                        else
                            endVerse = endVerse.substring(1);
                        if (endVerse.equals("0"))
                            endVerse = "1//G";
                        String xrefAbbr = abbrMap.get(xrefBookID);
                        if (xrefAbbr == null)
                            xrefAbbr = xrefBookID.getOsisID();
                        if (first)
                            first = false;
                        else
                            footnoteVisitor.visitText(" ");
                        if (xrefChapter == endChapter && !verse.equals("1//G") && !endVerse.equals("1//G") && Integer.parseInt(verse) > Integer.parseInt(endVerse)) {
                            String tmp = verse;
                            verse = endVerse;
                            endVerse = tmp;
                        }
                        footnoteVisitor.visitCrossReference(xrefAbbr, xrefBookID, xrefChapter, verse, endChapter, endVerse).visitText(xrefAbbr + " " + xrefChapter + ":" + verse);
                    }
                } else if (e3 instanceof PROLOG) {
                    PROLOG prolog = (PROLOG) e3;
                    if (prolog.getVref().intValue() != 1)
                        throw new IOException("" + prolog.getVref());
                    if (chapter.getProlog() != null)
                        throw new IOException("More than one prolog found");
                    FormattedText prologText = new FormattedText();
                    if (parseContent(prologText.getAppendVisitor(), prolog.getContent(), abbrMap)) {
                        prologText.trimWhitespace();
                        prologText.finished();
                        chapter.setProlog(prologText);
                    }
                } else if (e3 instanceof VERS) {
                    VERS vers = (VERS) e3;
                    int vnumber = vers.getVnumber().intValue();
                    if (lastvref != -1) {
                        if (lastvref != vnumber)
                            throw new IOException(lastvref + " != " + vnumber);
                        lastvref = -1;
                    }
                    Verse verse = new Verse("" + vnumber);
                    Visitor<RuntimeException> visitor = verse.getAppendVisitor();
                    boolean contentFound = false;
                    if (headlineBuffer.size() > 0) {
                        for (Headline h : headlineBuffer) {
                            h.accept(visitor.visitHeadline(h.getDepth()));
                        }
                        headlineBuffer.clear();
                        contentFound = true;
                    }
                    contentFound |= parseContent(visitor, vers.getContent(), abbrMap);
                    if (!contentFound) {
                        visitEmptyMarker(visitor);
                    }
                    verse.trimWhitespace();
                    chapter.getVerses().add(verse);
                } else {
                    throw new IOException(e3.getClass().toString());
                }
            }
            for (Verse v : chapter.getVerses()) v.finished();
        }
        result.getBooks().add(book);
    }
    return result;
}

Example 10 with FormattedText

use of biblemulticonverter.data.FormattedText in project BibleMultiConverter by schierlm.

the class OSIS method parseFormattedText.

protected void parseFormattedText(String verseName, Element root, FormattedText ft) {
    root.normalize();
    for (Node node = root.getFirstChild(); node != null; node = node.getNextSibling()) {
        if (node instanceof Text) {
            String text = node.getTextContent().replaceAll("[ \r\n\t]+", " ");
            if (text.startsWith(" ") && (node.getPreviousSibling() == null || Arrays.asList("brp", "lb", "title").contains(node.getPreviousSibling().getNodeName()))) {
                printWarning("WARNING: Whitespace at beginning of verse or after title/newline");
                text = text.substring(1);
            }
            Node ns = node.getNextSibling();
            while (ns != null && Arrays.asList("w", "q").contains(ns.getNodeName()) && ns.getFirstChild() == null) ns = ns.getNextSibling();
            if (text.endsWith(" ") && (ns == null || Arrays.asList("brp", "lb", "title").contains(ns.getNodeName()))) {
                printWarning("WARNING: Whitespace at end of verse or after title/newline");
                text = text.substring(0, text.length() - 1);
            }
            if (text.length() > 0)
                ft.getAppendVisitor().visitText(text);
        } else {
            Element elem = (Element) node;
            if (elem.getNodeName().equals("title")) {
                Headline hl = new Headline(2);
                if (elem.getAttribute("type").equals("chapter")) {
                    hl = new Headline(1);
                }
                if (elem.getChildNodes().getLength() == 1 && elem.getFirstChild() instanceof Text) {
                    String text = elem.getFirstChild().getTextContent();
                    if (!text.equals(text.trim())) {
                        printWarning("WARNING: Whitespace at beginning/end of headline: '" + text + "'");
                        elem.getFirstChild().setNodeValue(text.trim());
                    }
                }
                parseStructuredTextChildren(hl.getAppendVisitor(), elem);
                if (hl.getElementTypes(1).length() == 0) {
                    printWarning("WARNING: Empty headline in " + verseName);
                } else {
                    hl.accept(ft.getAppendVisitor().visitHeadline(hl.getDepth()));
                }
            } else {
                parseStructuredTextElement(ft.getAppendVisitor(), elem);
            }
        }
    }
}