feat: Develop comprehensive linting logic for genome quality and security

lib/lint.sh

@@ -0,0 +1,77 @@
+#!/usr/bin/env bash
+# =============================================================================
+# lib/lint.sh
+# Validation logic for Knowledge Genome files.
+# =============================================================================
+
+# Validates YAML frontmatter and mandatory fields
+lint_markdown_file() {
+  local file="$1"
+  local genome_name="$2"
+  local errors=0
+
+  # 1. Check Frontmatter delimiters
+  if [[ $(head -n 1 "$file") != "---" ]]; then
+    warn "Missing frontmatter start (---) in: $file"
+    errors=$((errors + 1))
+  fi
+
+  # 2. Check mandatory fields
+  local mandatory_fields=("title:" "type:" "domain:")
+  for field in "${mandatory_fields[@]}"; do
+    if ! grep -q "^${field}" "$file"; then
+      warn "Missing mandatory field '${field}' in: $file"
+      errors=$((errors + 1))
+    fi
+  done
+
+  # 3. Check if domain matches the genome name
+  if grep -q "^domain:" "$file" && ! grep -q "^domain: ${genome_name}" "$file"; then
+    warn "Domain mismatch in $file (expected ${genome_name})"
+    errors=$((errors + 1))
+  fi
+
+  return $errors
+}
+
+# Ensures files in private/ directories have the 'private: true' flag
+check_privacy_consistency() {
+  local file="$1"
+  local errors=0
+
+  if [[ "$file" == *"/private/"* ]]; then
+    if ! grep -q "^private: true" "$file"; then
+      error "Privacy Leak: $file is in a private folder but lacks 'private: true' metadata."
+      errors=$((errors + 1))
+    fi
+  else
+    if grep -q "^private: true" "$file"; then
+      warn "Metadata Mismatch: $file is marked private but located in a public directory."
+      # We count this as a warning unless you want to force strict isolation
+    fi
+  fi
+
+  return $errors
+}
+
+# Basic check for internal wiki-links [[target]]
+check_broken_links() {
+  local file="$1"
+  local base_dir
+  base_dir=$(dirname "$file")
+
+  # Extract links, stripping aliases: [[Link|Alias]] -> Link
+  local links
+  links=$(grep -oP '\[\[\K[^\]]+' "$file" | cut -d'|' -f1)
+
+  for link in $links; do
+    local target="$link"
+    [[ "$target" != *.md ]] && target="${target}.md"
+
+    # Simple relative check
+    if [[ ! -f "${base_dir}/${target}" && ! -f "${base_dir}/../${target}" ]]; then
+      # Only a warning as links might point to other genomes or deep structures
+      warn "Potential broken link: [[$link]] in $file"
+    fi
+  done
+}