mindnet_obsidian/src/mapping/sectionParser.ts

/**
 * Section parser: Split markdown by headings and extract wikilinks per section.
 */

export interface NoteSection {
  heading: string | null; // null for content before first heading
  headingLevel: number; // 0 for content before first heading
  content: string; // Full content of section (including heading)
  startLine: number; // Line index where section starts
  endLine: number; // Line index where section ends (exclusive)
  links: string[]; // Deduplicated wikilinks found in this section
  /** WP-26: Section type from `> [!section] type` callout in this section; null if not set. */
  sectionType: string | null;
  /** WP-26: Block ID from heading line (e.g. `## Title ^block-id`); null if not set. */
  blockId: string | null;
}

/** Match `> [!section] type` callout (type = word characters). */
const SECTION_CALLOUT_REGEX = /^\s*>\s*\[!section\]\s*(\S+)\s*$/i;
/** Match block ID at end of heading text: `... ^block-id`. */
const BLOCK_ID_IN_HEADING_REGEX = /\s+\^([a-zA-Z0-9_-]+)\s*$/;

/**
 * Split markdown content into sections by headings.
 */
export function splitIntoSections(markdown: string): NoteSection[] {
  const lines = markdown.split(/\r?\n/);
  const sections: NoteSection[] = [];
  
  let currentSection: NoteSection | null = null;
  let currentContent: string[] = [];
  let currentStartLine = 0;
  
  for (let i = 0; i < lines.length; i++) {
    const line = lines[i];
    if (line === undefined) continue;
    
    // Check if line is a heading
    const headingMatch = line.match(/^(#{1,6})\s+(.+)$/);
    
    if (headingMatch) {
      // Save previous section if exists
      if (currentSection !== null || currentContent.length > 0) {
        const content = currentContent.join("\n");
        const links = extractWikilinks(content);
        sections.push({
          heading: currentSection?.heading || null,
          headingLevel: currentSection?.headingLevel || 0,
          content,
          startLine: currentStartLine,
          endLine: i,
          links,
          sectionType: currentSection?.sectionType ?? null,
          blockId: currentSection?.blockId ?? null,
        });
      }

      // Start new section: extract blockId from heading text (e.g. "Title ^my-id")
      const headingLevel = (headingMatch[1]?.length || 0);
      const headingText = (headingMatch[2]?.trim() || "");
      const blockIdMatch = headingText.match(BLOCK_ID_IN_HEADING_REGEX);
      const blockId = blockIdMatch ? blockIdMatch[1] ?? null : null;
      currentSection = {
        heading: headingText,
        headingLevel,
        content: line,
        startLine: i,
        endLine: i + 1,
        links: [],
        sectionType: null,
        blockId,
      };
      currentContent = [line];
      currentStartLine = i;
    } else {
      // Add line to current section
      if (currentSection) {
        // WP-26: Detect `> [!section] type` callout (typically right after heading)
        const sectionCalloutMatch = line.match(SECTION_CALLOUT_REGEX);
        if (sectionCalloutMatch && sectionCalloutMatch[1]) {
          currentSection.sectionType = sectionCalloutMatch[1].trim();
        }
        currentContent.push(line);
        currentSection.content = currentContent.join("\n");
        currentSection.endLine = i + 1;
      } else {
        // Content before first heading
        currentContent.push(line);
      }
    }
  }
  
  // Save last section
  if (currentSection || currentContent.length > 0) {
    const content = currentContent.join("\n");
    const links = extractWikilinks(content);
    sections.push({
      heading: currentSection?.heading || null,
      headingLevel: currentSection?.headingLevel || 0,
      content,
      startLine: currentStartLine,
      endLine: lines.length,
      links,
      sectionType: currentSection?.sectionType ?? null,
      blockId: currentSection?.blockId ?? null,
    });
  }
  
  return sections;
}

/**
 * Extract all wikilinks from markdown text (deduplicated).
 */
export function extractWikilinks(markdown: string): string[] {
  const links = new Set<string>();
  const wikilinkRegex = /\[\[([^\]]+?)\]\]/g;
  
  let match: RegExpExecArray | null;
  while ((match = wikilinkRegex.exec(markdown)) !== null) {
    if (match[1]) {
      const target = match[1].trim();
      if (target) {
        // Check if it's a rel: link format [[rel:type|link]]
        if (target.startsWith("rel:")) {
          // Extract link part after |
          const parts = target.split("|");
          if (parts.length >= 2) {
            // It's [[rel:type|link]] format, extract the link part
            const linkPart = parts[1] || "";
            if (linkPart) {
              // Alias entfernen (|), Abschnitt (#) behalten für Edge-Block
              const linkTarget = linkPart.split("|")[0]?.trim() || linkPart;
              if (linkTarget) {
                links.add(linkTarget);
              }
            }
          }
        } else {
          // Normal link format [[link]] oder [[link#Abschnitt]]
          // Alias entfernen (|), Abschnitt (#) behalten für Edge-Block
          const linkTarget = target.split("|")[0]?.trim() || target;
          if (linkTarget) {
            links.add(linkTarget);
          }
        }
      }
    }
  }
  
  return Array.from(links).sort(); // Deterministic ordering
}