Keep every part when bookmark titles repeat in doc_split (#800) (#863)

crates/automation/src/lib.rs

@@ -1328,13 +1328,21 @@ impl Automation {
         let dir = self.resolve(a.str("out_dir")?, true)?;
         std::fs::create_dir_all(&dir).map_err(|e| failed(format!("{}: {e}", dir.display())))?;
         let mut files = Vec::new();
+        let mut used = std::collections::HashSet::new();
         for (i, (first, last, bytes)) in parts.iter().enumerate() {
             let safe = |t: &str| t.chars().map(|c| if c.is_alphanumeric() || " -_.,()".contains(c) { c } else { '_' }).collect::<String>();
             let file = match titles.iter().find(|t| t.0 + 1 == *first) {
                 Some((_, t)) => format!("{stem}-{}.pdf", safe(t)),
                 None => format!("{stem}-part{}.pdf", i + 1),
             };
-            let path = child(&dir, &file);
+            // Equal titles (or titles that sanitize alike) get -2, -3, ... so no part overwrites another; compared case-insensitively.
+            let mut unique = file.clone();
+            let mut n = 1;
+            while !used.insert(unique.to_lowercase()) {
+                n += 1;
+                unique = format!("{}-{n}.pdf", file.trim_end_matches(".pdf"));
+            }
+            let path = child(&dir, &unique);
             write_atomic(&path, bytes)?;
             files.push(json!({ "path": path.to_string_lossy(), "first_page": first, "last_page": last }));
         }

crates/automation/src/tools.rs

@@ -215,7 +215,7 @@ pub fn tools() -> Vec<ToolDef> {
                 }),
                 &["paths"],
             )),
-        t("doc_split", "Split a document", "Split into several files written to out_dir: every N pages, before given pages, at top-level bookmarks (bookmarks: true; files named after them), or by file size (max_mb). Files are <name>-partK.pdf.")
+        t("doc_split", "Split a document", "Split into several files written to out_dir: every N pages, before given pages, at top-level bookmarks (bookmarks: true; files named after them, repeated titles get -2, -3), or by file size (max_mb). Files are <name>-partK.pdf.")
             .cmd("page.split")
             .with(schema(
                 json!({ "doc": doc(), "every": { "type": "integer", "minimum": 1 }, "before": pages("that start a new part"), "bookmarks": { "type": "boolean" }, "max_mb": { "type": "number", "exclusiveMinimum": 0 }, "out_dir": { "type": "string" } }),

crates/automation/tests/automation.rs

@@ -2334,6 +2334,27 @@ fn stamps_through_tools() {
     assert!(matches!(a.call("stamp_custom", &json!({ "doc": doc, "page": 1, "path": "nope.png", "at": [1, 1] })), Err(ToolError::Failed(_))));
 }
 
+#[test]
+fn bookmark_split_with_equal_titles_keeps_every_part() {
+    let dir = workdir("organize_dup_titles");
+    let mut a = auto(&dir);
+    let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap();
+    ok(&mut a, "bookmark_add", json!({ "doc": doc, "title": "Same", "page": 1 }));
+    ok(&mut a, "bookmark_add", json!({ "doc": doc, "title": "Same", "page": 2 }));
+    ok(&mut a, "bookmark_add", json!({ "doc": doc, "title": "same", "page": 3 }));
+    let s = ok(&mut a, "doc_split", json!({ "doc": doc, "bookmarks": true, "out_dir": "parts" }));
+    let files: Vec<String> = s["files"]
+        .as_array()
+        .unwrap()
+        .iter()
+        .map(|f| std::path::Path::new(f["path"].as_str().unwrap()).file_name().unwrap().to_string_lossy().into_owned())
+        .collect();
+    assert_eq!(files, ["a-Same.pdf", "a-Same-2.pdf", "a-same-3.pdf"]);
+    for f in &files {
+        assert!(dir.join("parts").join(f).exists(), "{f} missing");
+    }
+}
+
 #[test]
 fn organizing_with_filters_bookmark_splits_and_extract_options() {
     let dir = workdir("organize2");

crates/ui-egui/src/files.rs

@@ -597,6 +597,7 @@ impl PdfCraftApp {
             }
         };
         let safe = |t: &str| t.chars().map(|c| if c.is_alphanumeric() || " -_.,()".contains(c) { c } else { '_' }).collect::<String>();
+        let mut used = std::collections::HashSet::new();
         let named: Vec<(String, Arc<Vec<u8>>)> = parts
             .into_iter()
             .map(|(a, b, bytes)| {
@@ -607,7 +608,14 @@ impl PdfCraftApp {
                     None if a == b => format!("{stem} (page {a}).pdf"),
                     None => format!("{stem} (pages {a}-{b}).pdf"),
                 };
-                (name, bytes)
+                // Equal titles (or titles that sanitize alike) get (2), (3), ... so no part overwrites another; compared case-insensitively.
+                let mut unique = name.clone();
+                let mut n = 1;
+                while !used.insert(unique.to_lowercase()) {
+                    n += 1;
+                    unique = format!("{} ({n}).pdf", name.trim_end_matches(".pdf"));
+                }
+                (unique, bytes)
             })
             .collect();
         self.write_files(&named, "Choose a folder for the split files");

crates/ui-egui/tests/editing.rs

@@ -1380,6 +1380,28 @@ fn split_dialog_writes_one_file_per_part() {
     let _ = std::fs::remove_dir_all(dir);
 }
 
+#[test]
+fn split_at_bookmarks_with_equal_titles_keeps_every_part() {
+    let dir = temp_path("split-dup-titles");
+    let _ = std::fs::remove_dir_all(&dir);
+    std::fs::create_dir_all(&dir).unwrap();
+    let mut h = organize(3);
+    h.state_mut().export_dir_override = Some(dir.to_string_lossy().into_owned());
+    for (index, title) in [(0, "Same"), (1, "Same"), (2, "same")] {
+        h.state_mut().apply_edit(pdfcraft_engine::Edit::AddBookmark { parent: vec![], index, title: title.into(), page: index });
+    }
+    h.state_mut().split_draft.mode = pdfcraft_ui_egui::SplitMode::Bookmarks;
+    h.state_mut().run_command("page.split");
+    h.run_steps(3);
+    h.get_by_label_contains("Creates 3 files from 3 pages");
+    h.get_by_label("Split").click();
+    h.run_steps(3);
+    let mut names: Vec<String> = std::fs::read_dir(&dir).unwrap().map(|e| e.unwrap().file_name().to_string_lossy().into_owned()).collect();
+    names.sort();
+    assert_eq!(names, ["doc - Same (2).pdf", "doc - Same.pdf", "doc - same (3).pdf"]);
+    let _ = std::fs::remove_dir_all(dir);
+}
+
 #[test]
 fn split_before_selected_pages() {
     let dir = temp_path("split-sel");