src/main/java/eu/svjatoslav/sixth/core/document/Document.java

   1 package eu.svjatoslav.sixth.core.document;
   2
   3 import eu.svjatoslav.commons.string.tokenizer.InvalidSyntaxException;
   4 import eu.svjatoslav.commons.string.tokenizer.Tokenizer;
   5 import eu.svjatoslav.commons.string.tokenizer.TokenizerMatch;
   6 import eu.svjatoslav.sixth.core.document.text.FormattedText;
   7
   8 import static eu.svjatoslav.commons.string.tokenizer.Terminator.TerminationStrategy.PRESERVE;
   9 import static eu.svjatoslav.sixth.core.document.Helper.*;
  10 import static eu.svjatoslav.sixth.core.document.text.FormattedText.fromOrg;
  11
  12 public class Document {
  13     public final Heading rootHeading = new Heading( null , 0, null);
  14     private Heading currentHeading = rootHeading;
  15
  16     public Heading createHeading(FormattedText name, int targetLevel){
  17         if (currentHeading.level == (targetLevel - 1)){
  18             Heading newHeading = new Heading(name, targetLevel, currentHeading);
  19             currentHeading.addChild(newHeading);
  20             currentHeading = newHeading;
  21             return newHeading;
  22         }
  23
  24         if (currentHeading.level > (targetLevel - 1)){
  25             currentHeading = currentHeading.parent;
  26             return createHeading(name, targetLevel);
  27         }
  28
  29         Heading missingIntermediate = new Heading(fromOrg("<noname>"), currentHeading.level + 1, currentHeading);
  30         currentHeading.addChild(missingIntermediate);
  31         currentHeading = missingIntermediate;
  32         return createHeading(name, targetLevel);
  33     }
  34
  35     public Heading getCurrentHeading(){
  36         return currentHeading;
  37     }
  38
  39     private void parseHeading(TokenizerMatch token) throws InvalidSyntaxException {
  40         String[] headingSections = token.getRegExpGroups();
  41         int level = headingSections[0].length();
  42         String title = headingSections[1];
  43         createHeading(fromOrg(title), level);
  44     }
  45
  46     public void parse(String fileContentsAsString) throws InvalidSyntaxException {
  47         final Tokenizer tokenizer = new Tokenizer(fileContentsAsString);
  48
  49         // Org heading:
  50         // "*** Example Heading 1234"
  51         tokenizer.addTerminator(PRESERVE, "(\\*+)[ \\t](.*)\\r?\\n", TG_HEADING);
  52
  53         // Org list. Examples:
  54         // "   + my list title"
  55         // "   - my list title"
  56         tokenizer.addTerminator(PRESERVE, "([ \\t]*)(\\+|-)[ \\t]+(.*)?\\r?\\n", TG_LIST);
  57
  58         // "   * my list title"
  59         tokenizer.addTerminator(PRESERVE, "([ \\t]+)(\\*)[ \\t]+(.*)?\\r?\\n", TG_LIST);
  60
  61         // TODO: add numbered list
  62
  63         // DocumentProperty:
  64         // "#+OPTIONS: H:20 num:20"
  65         tokenizer.addTerminator(PRESERVE, "#\\+([^\\s]+):(.*)\\r?\\n", TG_DOCUMENT_PROPERTY);
  66
  67         // Drawer property:
  68         //  " :ID:       533734b9-0456-4448-9830-a43646345615"
  69         tokenizer.addTerminator(PRESERVE, "([ \\t]*):([^\\s]+):(.*)\\r?\\n", TG_DRAWER_PROPERTY);
  70
  71
  72         // multiline code block
  73         tokenizer.addTerminator(PRESERVE,
  74                 "([ \\t]*)#\\+BEGIN_SRC" +  // source begin identifier
  75                         "(([ \\t]+)(.*))?(\\r?\\n)" + // source block parameters
  76                         "((?:.|\\n|\\r)*?)" + // source content
  77                         "(\\r?\\n)([ \\t]*)#\\+END_SRC(.*)\\r?\\n" // source end identifier
  78                 , TG_MULTILINE_CODE);
  79
  80         // verse
  81         tokenizer.addTerminator(PRESERVE,
  82                 "([ \\t]*)#\\+BEGIN_VERSE" + // verse begin identifier
  83                         "(([ \\t]+)(.*))?(\\r?\\n)" + // verse block parameters
  84                         "((?:.|\\n|\\r)*?)" + // verse
  85                         "(\\r?\\n)([ \\t]*)#\\+END_VERSE(.*)\\r?\\n" // verse end identifier
  86                 , TG_VERSE);
  87
  88
  89         // TODO: add support for export blocks:
  90         //        #+begin_export latex
  91         //  \clearpage
  92         //#+end_export
  93
  94
  95         // normal text
  96         tokenizer.addTerminator(PRESERVE,".*\\r?\\n", TG_NORMAL_TEXT);
  97
  98         while (tokenizer.hasMoreContent()) {
  99             final TokenizerMatch tm = tokenizer.getNextToken();
 100
 101             if (tm.isGroup(TG_HEADING)){
 102                 parseHeading(tm);
 103                 continue;
 104             }
 105
 106             currentHeading.parse(tm);
 107         }
 108
 109     }
 110 }