allow for text child nodes when building tag index

pdf-raku · Nov 17, 2023 · 3ce2214 · 3ce2214
1 parent 75a2f88
commit 3ce2214
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 2 deletions.
diff --git a/docs/index.md b/docs/index.md
@@ -40,7 +40,7 @@ Scripts in this Distribution
 
 ### `pdf-tag-dump.raku`
 
-    pdf-tag-dump.raku --select=<xpath-expr> --omit=tag --password=Xxxx --max-depth=n --marks --/atts --/style --debug t/pdf/tagged.pdf
+    pdf-tag-dump.raku --select=<xpath-expr> --omit=tag --password=Xxxx --max-depth=n --marks --artifacts --/atts --/style --debug t/pdf/tagged.pdf
 
 Options:
 
@@ -54,6 +54,8 @@ Options:
 
   * `--marks` - descend into marked content
 
+  * `--artifacts` - include artifact structure and content
+
   * `--strict` - warn about unknown tags, etc
 
   * `--/style` - omit stylesheet

diff --git a/lib/PDF/Tags/Reader.rakumod b/lib/PDF/Tags/Reader.rakumod
@@ -31,7 +31,7 @@ method read(PDF::Class:D :$pdf!, Bool :$create, |c --> PDF::Tags:D) {
 constant Tags = Hash[PDF::Content::Tag];
 has Tags %!canvas-tags{PDF::Content::Canvas};
 
-sub build-tag-index(%tags, PDF::Content::Tag $tag) {
+multi sub build-tag-index(%tags, PDF::Content::Tag $tag) {
     with $tag.mcid {
         %tags{$_} = $tag;
     }
@@ -41,6 +41,8 @@ sub build-tag-index(%tags, PDF::Content::Tag $tag) {
     }
 }
 
+multi sub build-tag-index(%, Str) { }
+
 multi sub tag-text(PDF::Content::Tag:D $tag) {
     with $tag.attributes<ActualText> {
         PDF::COS::TextString.COERCE: $_
@@ -49,6 +51,7 @@ multi sub tag-text(PDF::Content::Tag:D $tag) {
         $tag.kids.map(&tag-text).join
     }
 }
+
 multi sub tag-text(Str:D $text) { $text }
 
 method canvas-tags($canvas --> Hash) {