package eu.svjatoslav.sixth.core.document;
-import eu.svjatoslav.commons.string.String2;
import eu.svjatoslav.commons.string.tokenizer.InvalidSyntaxException;
import eu.svjatoslav.commons.string.tokenizer.Tokenizer;
import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
return createHeading(name, targetLevel);
}
- try {
- Heading missingIntermediate = new Heading(fromOrg("<noname>"), currentHeading.level + 1, currentHeading);
- currentHeading.addChild(missingIntermediate);
- currentHeading = missingIntermediate;
- return createHeading(name, targetLevel);
- } catch (InvalidSyntaxException e) {
- throw new IllegalStateException("impossible situation");
- }
+ Heading missingIntermediate = new Heading(fromOrg("<noname>"), currentHeading.level + 1, currentHeading);
+ currentHeading.addChild(missingIntermediate);
+ currentHeading = missingIntermediate;
+ return createHeading(name, targetLevel);
}
public Heading getCurrentHeading(){
}
private void parseHeading(TokenizerMatch token) throws InvalidSyntaxException {
- // expected sample heading:
- // ***** test heading
-
- String[] headingSections = String2.getGroups(token.token, "(\\*+)[ \\t](.*)\\r?\\n");
+ String[] headingSections = token.getRegExpGroups();
int level = headingSections[0].length();
String title = headingSections[1];
createHeading(fromOrg(title), level);
// Org heading:
// "*** Example Heading 1234"
- tokenizer.addTerminator(PRESERVE, "\\*+[ \\t].*\\r?\\n", TG_HEADING);
+ tokenizer.addTerminator(PRESERVE, "(\\*+)[ \\t](.*)\\r?\\n", TG_HEADING);
// Org list. Examples:
// " + my list title"
// " - my list title"
- tokenizer.addTerminator(PRESERVE, "[ \\t]*(\\+|-)([ \\t].*)?\\r?\\n", TG_LIST);
+ tokenizer.addTerminator(PRESERVE, "([ \\t]*)(\\+|-)[ \\t]?(.*)?\\r?\\n", TG_LIST);
// " * my list title"
- tokenizer.addTerminator(PRESERVE, "[ \\t]+\\*([ \\t].*)?\\r?\\n", TG_LIST);
+ tokenizer.addTerminator(PRESERVE, "([ \\t]+)(\\*)[ \\t]?(.*)?\\r?\\n", TG_LIST);
// DocumentProperty:
// "#+OPTIONS: H:20 num:20"
continue;
}
- tokenizer.unreadToken();
- currentHeading.parse(tokenizer);
+ currentHeading.parse(tm);
}
}
package eu.svjatoslav.sixth.core.document;
-import eu.svjatoslav.commons.string.tokenizer.InvalidSyntaxException;
import eu.svjatoslav.commons.string.tokenizer.Tokenizer;
import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
+import eu.svjatoslav.sixth.core.document.content.ListElement;
import eu.svjatoslav.sixth.core.document.text.FormattedText;
import java.util.ArrayList;
import java.util.List;
-import static eu.svjatoslav.sixth.core.document.Helper.TG_DOCUMENT_PROPERTY;
import static eu.svjatoslav.sixth.core.document.Helper.TG_LIST;
-import static eu.svjatoslav.sixth.core.document.text.FormattedText.fromOrg;
public class Heading {
public final FormattedText name;
public final Heading parent;
private final List<Heading> children = new ArrayList<>();
- public final ListElement rootListElement = new ListElement(null, 0, null);
+ public final ListElement rootListElement = new ListElement(null, -1, null, "");
private ListElement currentListElement = rootListElement;
public Heading(FormattedText name, int level, Heading parent){
if (level > 0) sb.append(enlistTitleInMD());
- // sb.append(unparsedContent);
-
+ rootListElement.toMD(sb, -2);
children.stream().map(Heading::toMD).forEach(sb::append);
for (int i = 0; i < level; i++)
sb.append("#");
- sb.append(" ").append(name.compileMd()).append("\n");
+ sb.append(" ").append(name.toMD()).append("\n");
return sb.toString();
}
- public ListElement createListElement(FormattedText name, int targetLevel){
- if (currentListElement.level == (targetLevel - 1)){
- ListElement newListElement = new ListElement(name, targetLevel, currentListElement);
- currentListElement.addChild(newListElement);
- currentListElement = newListElement;
- return newListElement;
- }
+ public ListElement getCurrentHeading(){
+ return currentListElement;
+ }
- if (currentListElement.level > (targetLevel - 1)){
- currentListElement = currentListElement.parent;
- return createListElement(name, targetLevel);
- }
+ public void parse(TokenizerMatch tm){
- try {
- ListElement missingIntermediate = new ListElement(
- fromOrg("<noname>"), currentListElement.level + 1, currentListElement);
- currentListElement.addChild(missingIntermediate);
- currentListElement = missingIntermediate;
- return createListElement(name, targetLevel);
- } catch (InvalidSyntaxException e) {
- throw new IllegalStateException("impossible situation");
+ if (tm.isGroup(TG_LIST)){
+ parseList(tm);
+ return;
}
+
+ currentListElement.parse(tm);
}
- public ListElement getCurrentHeading(){
- return currentListElement;
+ private void parseList(TokenizerMatch tm) {
+ String[] listSections = tm.getRegExpGroups();
+ int indent = listSections[0].length();
+ String type = listSections[1];
+
+ FormattedText title = FormattedText.fromOrg(parseFullListTitle(listSections.length > 2 ? listSections[2] : "", tm.getTokenizer(), indent));
+
+// System.out.println(" indent: " + indent);
+// System.out.println(" type: " + type);
+// System.out.println(" title: " + title);
+
+ ListElement parent = null;
+
+ if (indent > currentListElement.indent){
+ ListElement newElement = new ListElement(title, indent, parent, type);
+ currentListElement.addContent(newElement);
+ currentListElement = newElement;
+ }
+
}
- public void parse(Tokenizer tokenizer){
- while (tokenizer.hasMoreContent()) {
- final TokenizerMatch tm = tokenizer.getNextToken();
- if (tm.isGroup(TG_LIST)){
- System.out.println("LIST!: " + tm.token);
- continue;
- }
+ private String parseFullListTitle(String partialTitle, Tokenizer tokenizer, int listIndent){
+ StringBuilder sb = new StringBuilder();
+ sb.append(partialTitle);
- if (tm.isGroup(TG_DOCUMENT_PROPERTY)){
-// System.out.println("DOCUMENT PROPERTY!!!: " + tm.token);
- continue;
- }
+ while (tokenizer.hasMoreContent()){
+ final TokenizerMatch tm = tokenizer.getNextToken();
- if (tm.isGroup(null)){
- System.out.println("unhandled \"" + tm.token + "\"");
+ if (isContentContinuation(tm, listIndent, null)){
+ String titleContinuation = tm.token.substring(listIndent).trim();
+ sb.append("\n").append(titleContinuation);
continue;
}
tokenizer.unreadToken();
break;
}
+
+ return sb.toString();
}
+
+ public static boolean isContentContinuation(TokenizerMatch tm, int requiredIndent, String requiredGroup) {
+ if (tm.token.length() <= requiredIndent) return false;
+
+ return tm.isGroup(requiredGroup) && tm.token.substring(0, requiredIndent +1).trim().length() == 0;
+ }
+
}
+++ /dev/null
-package eu.svjatoslav.sixth.core.document;
-
-import eu.svjatoslav.commons.string.tokenizer.Tokenizer;
-import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
-import eu.svjatoslav.sixth.core.document.text.FormattedText;
-
-import java.util.ArrayList;
-import java.util.List;
-
-import static eu.svjatoslav.sixth.core.document.Helper.TG_DOCUMENT_PROPERTY;
-
-public class ListElement {
- public final FormattedText name;
- public final int level;
- public final ListElement parent;
- private final List<ListElement> children = new ArrayList<>();
-
- public ListElement(FormattedText name, int level, ListElement parent){
- this.level = level;
- this.name = name;
- this.parent = parent;
- }
-
- public void addChild(ListElement listElement){
- children.add(listElement);
- }
-
- public void parse(Tokenizer tokenizer){
- while (tokenizer.hasMoreContent()) {
- final TokenizerMatch tm = tokenizer.getNextToken();
-
- if (tm.isGroup(TG_DOCUMENT_PROPERTY)){
- System.out.println("DOCUMENT PROPERT!!!: " + tm.token);
- continue;
- }
-
- if (tm.isGroup(null)){
- System.out.println(" HC: " + tm.token);
- continue;
- }
-
- tokenizer.unreadToken();
- break;
- }
- }
-
-
-
-}
package eu.svjatoslav.sixth.core.document.content;
public interface Content {
+ void toMD(StringBuilder sb, int indent);
}
--- /dev/null
+package eu.svjatoslav.sixth.core.document.content;
+
+import eu.svjatoslav.commons.string.String2;
+import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
+import eu.svjatoslav.sixth.core.document.text.FormattedText;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import static eu.svjatoslav.sixth.core.document.Helper.TG_DOCUMENT_PROPERTY;
+
+public class ListElement implements Content {
+ public final FormattedText name;
+ public final int indent;
+ public final ListElement parent;
+ private String type;
+ private final List<Content> content = new ArrayList<>();
+
+ public ListElement(FormattedText name, int indent, ListElement parent, String type) {
+ this.indent = indent;
+ this.name = name;
+ this.parent = parent;
+ this.type = type;
+ }
+
+ public void addContent(ListElement content) {
+ this.content.add(content);
+ }
+
+ public void parse(TokenizerMatch tm) {
+
+ if (tm.isGroup(TG_DOCUMENT_PROPERTY)) {
+// System.out.println("DOCUMENT PROPERT!!!: " + tm.token);
+ return;
+ }
+
+ if (tm.isGroup(null)) {
+// System.out.println(" Plain text content: " + tm.token);
+ return;
+ }
+
+ System.out.println("ERROR!!!! Unable to handle: " + tm);
+
+ }
+
+
+ public void toMD(StringBuilder sb, int i) {
+ if (indent >= 0){
+ String2 s = new String2();
+ s.addSuffix(" ", indent).addSuffix(type).addSuffix(" ").addSuffix(name.toMD()).addSuffix("\n");
+ sb.append(s.toString());
+ }
+
+ for (Content c : content) {
+ c.toMD(sb, indent + 2);
+ }
+ }
+}
private Map<String, String> propertyToValue = new HashMap<>();
+ @Override
+ public void toMD(StringBuilder sb, int indent) {
+ // TODO
+ }
}
public class TextBlock implements Content {
private FormattedText text;
+
+ @Override
+ public void toMD(StringBuilder sb, int indent) {
+ // TODO
+ // sb.append(text.toMD());
+ }
}
package eu.svjatoslav.sixth.core.document.text;
-import eu.svjatoslav.commons.string.tokenizer.InvalidSyntaxException;
import eu.svjatoslav.commons.string.tokenizer.Tokenizer;
import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
import java.util.ArrayList;
import java.util.List;
+import static eu.svjatoslav.sixth.core.document.Helper.TG_HYPERLINK;
+
public class FormattedText {
List<FormattedTextElement> elements = new ArrayList<>();
- public void parseOrgSyntax(String orgText) throws InvalidSyntaxException {
+ public void parseOrgSyntax(String orgText) {
Tokenizer tokenizer = getTokenizer(orgText);
while (tokenizer.hasMoreContent()) {
final TokenizerMatch token = tokenizer.getNextToken();
- if (token.terminator == Hyperlink.orgTerminator){
+ if (token.isGroup(TG_HYPERLINK)){
elements.add(Hyperlink.fromOrg(token));
continue;
}
}
- public static FormattedText fromOrg(String orgText) throws InvalidSyntaxException {
+ public static FormattedText fromOrg(String orgText){
FormattedText formattedText = new FormattedText();
formattedText.parseOrgSyntax(orgText);
return formattedText;
}
- public String compileMd(){
+ public String toMD(){
StringBuilder sb = new StringBuilder();
for (FormattedTextElement element : elements)
- sb.append(element.compileMd());
+ sb.append(element.toMD());
return sb.toString();
}
private Tokenizer getTokenizer(String contents) {
final Tokenizer tokenizer = new Tokenizer(contents);
tokenizer.addTerminator(Hyperlink.orgTerminator);
+ tokenizer.addTerminator(Hyperlink.orgTerminator2);
return tokenizer;
}
package eu.svjatoslav.sixth.core.document.text;
public interface FormattedTextElement {
- String compileMd();
+ String toMD();
}
package eu.svjatoslav.sixth.core.document.text;
-import eu.svjatoslav.commons.string.tokenizer.InvalidSyntaxException;
import eu.svjatoslav.commons.string.tokenizer.Terminator;
import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
public class Hyperlink implements FormattedTextElement {
public static final Terminator orgTerminator =
- new Terminator(PRESERVE, "\\[\\[.*\\]\\]", TG_HYPERLINK);
+ new Terminator(PRESERVE, "\\[\\[(.+)\\][ \\t]*\\[(.+)\\]\\]", TG_HYPERLINK);
+
+ public static final Terminator orgTerminator2 =
+ new Terminator(PRESERVE, "\\[\\[(.*)\\]\\]", TG_HYPERLINK);
private String label;
private String URL;
@Override
- public String compileMd() {
+ public String toMD() {
return "<URL: " + URL + ", LABEL: " + label + ">";
}
- public static Hyperlink fromOrg(TokenizerMatch tokenizerMatch) throws InvalidSyntaxException {
+ public static Hyperlink fromOrg(TokenizerMatch tokenizerMatch) {
Hyperlink hyperlink = new Hyperlink();
- hyperlink.parseOrgSyntax(tokenizerMatch);
+ hyperlink.parseOrg(tokenizerMatch);
return hyperlink;
}
- private void parseOrgSyntax(TokenizerMatch tokenizerMatch) throws InvalidSyntaxException {
-// Tokenizer tokenizer = new Tokenizer(tokenizerMatch.reminder);
-// Terminator linkSeparator = tokenizer.addTerminator("][", PRESERVE);
-//
-// URL = tokenizer.expectAndConsumeNextTerminatorToken(null).token;
-//
-// if (tokenizer.hasMoreContent()){ // link label is optional
-// tokenizer.expectAndConsumeNextTerminatorToken(linkSeparator);
-// label = tokenizer.expectAndConsumeNextTerminatorToken(null).token;
-// }
+ private void parseOrg(TokenizerMatch tokenizerMatch) {
+ String[] regExpGroups = tokenizerMatch.getRegExpGroups();
+ URL = regExpGroups[0];
+ if (tokenizerMatch.terminator == orgTerminator){
+ label = regExpGroups[1];
+ }
+
}
}
}
@Override
- public String compileMd() {
+ public String toMD() {
return content;
}
}
projects / sixth.git / commitdiff