1 files changed, 101 insertions, 17 deletions

diff --git a/src/file_pane.zig b/src/file_pane.zig
index 739d7b54..b164a7b3 100644
--- a/src/file_pane.zig
+++ b/src/file_pane.zig
@@ -15,13 +15,63 @@ const look = @import("look.zig");
 const syntax = @import("syntax.zig");
 const tracy = @import("tracy.zig");
 
-const SYNTAX_CONTEXT_BEFORE_ROWS: usize = 0;
 const SYNTAX_CONTEXT_AFTER_ROWS: usize = 2;
 
 pub fn lineCount(content: []const u8) usize {
     return std.mem.count(u8, content, "\n") + 1;
 }
 
+/// THE LINE INDEX, built on demand: `line_starts[i]` is the byte offset where
+/// line i begins and its length is the line count. Without it, every question
+/// about lines is a scan from byte 0, and a file pane asks several of them per
+/// keystroke — the scrollbar's total, the scroll clamp, the syntax window's
+/// bounds, the body's first visible line. On a 300k-line file that was ~35% of
+/// the whole frame, and it is what made a single `j` cost 25ms.
+///
+/// INVALIDATION — the part that rots if nobody says it out loud. The index is
+/// dropped in EXACTLY ONE PLACE: setContent, immediately below, which is the
+/// funnel every content swap in the editor already goes through (typing, undo,
+/// redo, a save's normalisation, an output buffer refilling itself). A File
+/// built by a struct literal starts with an empty index, and empty reads as
+/// "not built yet" — a real index always has at least one entry, because a
+/// file always has at least one line. So there is one and only one way to make
+/// this wrong: assign `f.content` without going through setContent. Don't.
+///
+/// Fails only when the index could not be allocated. nlines and lineStart
+/// swallow that and scan the old way, so OOM there is slow rather than wrong;
+/// callers that need the whole table say `try` and drop the keystroke, which
+/// is what they already did when their own arena ran out.
+pub fn lineIndex(gpa: std.mem.Allocator, f: *File) ![]const usize {
+    if (f.line_starts.len > 0) return f.line_starts;
+    // exact alloc, not an ArrayList: deinitPane frees `line_starts` itself, and
+    // an ArrayList's items slice is shorter than its allocation whenever the
+    // growth strategy rounded up — freeing that is a wrong-size free.
+    const starts = try gpa.alloc(usize, lineCount(f.content));
+    starts[0] = 0;
+    var i: usize = 1;
+    var off: usize = 0;
+    while (std.mem.indexOfScalarPos(u8, f.content, off, '\n')) |nl| {
+        off = nl + 1;
+        starts[i] = off;
+        i += 1;
+    }
+    f.line_starts = starts;
+    return starts;
+}
+
+/// line count, O(1) once the index is warm
+pub fn nlines(gpa: std.mem.Allocator, f: *File) usize {
+    const idx = lineIndex(gpa, f) catch return lineCount(f.content);
+    return idx.len;
+}
+
+/// byte offset of line `row`, or content.len past the end — modal
+/// .lineStartOffset's contract exactly, without its walk
+pub fn lineStart(gpa: std.mem.Allocator, f: *File, row: usize) usize {
+    const idx = lineIndex(gpa, f) catch return modal.lineStartOffset(f.content, row);
+    return if (row >= idx.len) f.content.len else idx[row];
+}
+
 pub fn open(p: *Pardes, id: usize, path: []const u8, line: usize) !*Pane {
     const content = try look.readFile(p.gpa, path);
     errdefer p.gpa.free(content);
@@ -39,9 +89,19 @@ pub fn open(p: *Pardes, id: usize, path: []const u8, line: usize) !*Pane {
     return pane;
 }
 
+/// The ONE content swap. Everything that edits a file pane lands here, which
+/// is what lets the line index above have a single invalidation point.
 pub fn setContent(p: *Pardes, f: *File, new: []u8) void {
     p.gpa.free(f.content);
     f.content = new;
+    if (f.line_starts.len > 0) p.gpa.free(f.line_starts);
+    f.line_starts = &.{};
+    // the highlights go too, and not just because they are stale: their byte
+    // range is what refreshHighlights tests a scroll against, and a range
+    // measured on the OLD content would let it skip a re-parse it needs
+    if (f.highlights.len > 0) p.gpa.free(f.highlights);
+    f.highlights = &.{};
+    f.highlight_start = 0;
     f.syntax_dirty = true;
 }
 
@@ -49,8 +109,8 @@ pub fn setContent(p: *Pardes, f: *File, new: []u8) void {
 /// selections in its history transactions), clamped: the content it was taken
 /// against may be shorter than the one it is being restored onto.
 pub fn restoreSnap(pane: *Pane, f: *File, snap: FileSnap) void {
-    const n = modal.lineCount(f.content);
-    const row: usize = @min(@as(usize, @intCast(@max(0, snap.cur_row))), if (n == 0) 0 else n - 1);
+    const n = nlines(pane.gpa, f);
+    const row: usize = @min(@as(usize, @intCast(@max(0, snap.cur_row))), n - 1);
     const llen = modal.lineSlice(f.content, row).len;
     pane.cur_row = @intCast(row);
     pane.cur_col = @intCast(@min(@as(usize, @intCast(@max(0, snap.cur_col))), llen));
@@ -78,10 +138,35 @@ pub fn refreshHighlights(p: *Pardes) void {
             f.syntax_dirty = false;
             continue;
         }
-        const start_row = f.scroll -| SYNTAX_CONTEXT_BEFORE_ROWS;
-        const start = modal.lineStartOffset(f.content, start_row);
-        const end_row = start_row + SYNTAX_CONTEXT_BEFORE_ROWS + pane.rows + SYNTAX_CONTEXT_AFTER_ROWS;
-        const end = @max(start, modal.lineStartOffset(f.content, end_row));
+        // What the screen needs coloured right now. If the last parse still
+        // covers it, this scroll is free — and that is the whole point of the
+        // slack below. Highlights only ever survive while the CONTENT does:
+        // setContent throws them away, so these byte offsets cannot be stale.
+        const need_start = lineStart(p.gpa, f, f.scroll);
+        const need_end = @max(need_start, lineStart(p.gpa, f, f.scroll + pane.rows + SYNTAX_CONTEXT_AFTER_ROWS));
+        if (f.highlights.len > 0 and need_start >= f.highlight_start and
+            need_end <= f.highlight_start + f.highlights.len)
+        {
+            f.syntax_dirty = false;
+            continue;
+        }
+        // How much MORE than the screen to parse. An edit or a fresh open has
+        // no previous parse to widen (setContent throws the highlights away),
+        // and slack would be pure loss there: every keystroke of typing pays
+        // this parse and none of it is amortised over anything. A SCROLL that
+        // outran the covered range is the opposite case — take a screenful
+        // above and below and the next ~pane.rows rows cost nothing at all.
+        // Scrolling used to re-parse the visible window on every single row,
+        // which on a file with 8000-column lines is a third of a megabyte per
+        // keypress. Three screens once beats one screen forty times.
+        //
+        // The slack also means those lines are parsed with real context above
+        // them, so a construct that opens off-screen now colours correctly —
+        // a fidelity gain, and one that cannot reach a file shown from the top
+        // (scroll 0 clamps the window to exactly what it always was).
+        const slack: usize = if (f.highlights.len == 0) 0 else pane.rows;
+        const start = lineStart(p.gpa, f, f.scroll -| slack);
+        const end = @max(start, lineStart(p.gpa, f, f.scroll + pane.rows + SYNTAX_CONTEXT_AFTER_ROWS + slack));
         const new_highlights = syntax.highlightFileRange(p.gpa, f.path, f.content, start, end) catch {
             f.syntax_dirty = false;
             continue;
@@ -97,11 +182,13 @@ pub fn refreshHighlights(p: *Pardes) void {
 /// offset, each behind its right-aligned line number, then cut by hscroll.
 pub fn bodyText(arena: std.mem.Allocator, pane: *Pane, f: *File) ![]const u8 {
     var out: std.ArrayList(u8) = .empty;
-    var flines = std.mem.splitScalar(u8, f.content, '\n');
-    var skipped: usize = 0;
-    while (skipped < f.scroll) : (skipped += 1) {
-        if (flines.next() == null) break;
-    }
+    // start ON the first visible line instead of walking the file to it: this
+    // walk was O(f.scroll) and recolorSyntax below ran the identical one again
+    var flines = std.mem.splitScalar(u8, f.content[lineStart(pane.gpa, f, f.scroll)..], '\n');
+    // scrolled past EOF (an edit shortened the file under a stale scroll): the
+    // old walk left the iterator dry, so drop the one empty line a slice split
+    // still yields, or the body grows a phantom numbered row
+    if (f.scroll >= nlines(pane.gpa, f)) _ = flines.next();
     var i: usize = 0;
     while (i < pane.rows) : (i += 1) {
         if (i > 0) try out.append(arena, '\n');
@@ -174,11 +261,8 @@ pub fn recolorSyntax(p: *Pardes, pane: *Pane, f: *File, r: pardes.Rect, tx: u16,
     const s = &p.surface;
     const tz_recolor = tracy.zone(@src(), "synRecolor");
     defer tz_recolor.end();
-    var flines = std.mem.splitScalar(u8, f.content, '\n');
-    var skip: usize = 0;
-    while (skip < f.scroll) : (skip += 1) {
-        if (flines.next() == null) break;
-    }
+    // indexed start, same as bodyText — an empty tail simply paints nothing
+    var flines = std.mem.splitScalar(u8, f.content[lineStart(p.gpa, f, f.scroll)..], '\n');
     const hs: usize = @intCast(@max(0, pane.hscroll));
     var vr: u16 = 0;
     while (vr < body_h) : (vr += 1) {