The collection's UCS2 CMap is parsed the first time a code needs it

A font whose /ToUnicode maps every code it shows never parses it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pq7HyDBXygTf7jcqdsjcfn

vendor/hayro-interpret/src/font/cid.rs

@@ -6,6 +6,7 @@ use crate::font::{
 };
 use crate::{CMapResolverFn, CacheKey, FontResolverFn};
 use hayro_cmap::{BfString, CMap, CharacterCollection, CidFamily, WritingMode};
+use std::sync::OnceLock;
 use hayro_syntax::object;
 use hayro_syntax::object::Dict;
 use hayro_syntax::object::Name;
@@ -44,7 +45,7 @@ pub(crate) struct Type0Font {
     to_unicode_is_cid_indexed: bool,
     /// PdfCraft patch (84): the character collection's UCS2 CMap (by CID), for the codes the
     /// font's own `/ToUnicode` gives nothing for, whether or not its program is embedded.
-    ucs2: Option<CMap>,
+    ucs2: Option<Ucs2>,
     /// PdfCraft patch: whether the CIDs belong to an Adobe character collection (Japan1, GB1,
     /// CNS1, Korea1), whose glyph numbering no substitute other than a CID-keyed CFF font shares.
     adobe_collection: bool,
@@ -140,13 +141,10 @@ impl Type0Font {
             .as_ref()
             .and_then(|cc| cc.family.ucs2_cmap())
             .and_then(|name| (cmap_resolver)(name))
-            .and_then(|data| {
-                let resolver = cmap_resolver.clone();
-                CMap::parse(data, move |n| (resolver)(n))
-            });
+            .map(|data| Ucs2 { data, resolver: cmap_resolver.clone(), map: OnceLock::new() });
         // If there is no ToUnicode map, try to get the UCS2 CMap.
-        if fallback && to_unicode.is_none() && ucs2.is_some() {
-            to_unicode = ucs2.take();
+        if fallback && to_unicode.is_none() && let Some(ucs2_cmap) = ucs2.take().and_then(|u| u.parse()) {
+            to_unicode = Some(ucs2_cmap);
             to_unicode_is_cid_indexed = true;
         }
 
@@ -477,7 +475,7 @@ impl Type0Font {
             }
         }
         // PdfCraft patch (84): then the collection's UCS2 CMap, by the code's CID.
-        if let Some(ucs2) = &self.ucs2
+        if let Some(ucs2) = self.ucs2.as_ref().and_then(Ucs2::cmap)
             && let Some(s) = self.code_to_cid(code).and_then(|cid| ucs2.lookup_bf_string(cid))
         {
             return Some(s);
@@ -487,6 +485,31 @@ impl Type0Font {
     }
 }
 
+/// PdfCraft patch (84): a collection's UCS2 CMap, parsed the first time a code needs it: a font
+/// whose `/ToUnicode` maps every code it shows never parses it.
+struct Ucs2 {
+    data: &'static [u8],
+    resolver: CMapResolverFn,
+    map: OnceLock<Option<CMap>>,
+}
+
+impl Ucs2 {
+    fn parse(&self) -> Option<CMap> {
+        let resolver = self.resolver.clone();
+        CMap::parse(self.data, move |n| (resolver)(n))
+    }
+
+    fn cmap(&self) -> Option<&CMap> {
+        self.map.get_or_init(|| self.parse()).as_ref()
+    }
+}
+
+impl std::fmt::Debug for Ucs2 {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("Ucs2").field("bytes", &self.data.len()).finish_non_exhaustive()
+    }
+}
+
 impl CacheKey for Type0Font {
     fn cache_key(&self) -> u128 {
         self.cache_key