Preserve a box's own top margin at a forced page break

Confirmed gap: BlockFragmentation.TryGetForcedBreakTarget's targetTop was
always the raw page-content-top boundary - the box's own MarginTopCollapse
was used only to decide WHICH slot the natural (unshifted) position falls
in, never added back into the actual placement. css-break-3 5.2 preserves
(does not truncate) a box's own margin specifically at a FORCED break -
truncation only applies to an UNFORCED break where a margin alone happens
to cross a page boundary (BlockFragmentation.ResolveBlockTop, unaffected by
this change).

Fixed at the two places breakTop actually becomes a box's placement
(Dom/CssBox.cs): the immediate-placement path (top = breakTop) and the
deferred-pass path (RequestedBreakBeforeTop, which flows through
BlockBreakToken.ResumeTopOverride into _resumeTopOverride on the resuming
pass) - not inside TryGetForcedBreakTarget itself, which stays a pure
boundary value on purpose (its own slot/target output is asserted directly
in ForcedBreakTargetIsTheFramesTests.cs and needs to keep meaning "the
boundary", not "the boundary plus whatever margin happened to apply").

Un-ignores TargetIsTheBoundary_AndThePreservedMarginIsAddedToIt
(HtmlRenderer.Test, ported in Batch 1) and
ForcedBreak_MarginAfterBreak_IsPreservedNotTruncated
(HtmlRenderer.IntegrationTest, ported in Batch 2).

Full suite: HtmlRenderer.Test 2428 passed/127 skipped/0 failed (was
2427/128), HtmlRenderer.IntegrationTest 335 passed/91 skipped/0 failed (was
334/92), HtmlRenderer.PdfSharp.Test 39 passed/0 failed (unchanged).

Author: jhaygood86

Source/HtmlRenderer/Core/Dom/CssBox.cs

@@ -895,14 +895,22 @@ protected virtual void PerformLayoutImp(RGraphics g)
                         }
                         else if (BlockFragmentation.TryGetForcedBreakTarget(this, prevSibling, baseTopWithoutMargin, out var breakSlot, out var breakTop))
                         {
+                            // css-break-3 5.2 preserves a box's own top margin at a FORCED break (unlike an
+                            // unforced one, where BlockFragmentation.ResolveBlockTop truncates it to avoid
+                            // paginating through blank space) - breakTop itself is the page's own content
+                            // top (TryGetForcedBreakTarget's own contract, kept a pure boundary value so its
+                            // slot/target stay meaningful on their own), so the margin is added here, once,
+                            // at the point it becomes this box's actual placement.
+                            var breakTopWithMargin = breakTop + MarginTopCollapse(prevSibling);
+
                             if (CanDeferToLaterPass())
                             {
                                 // A forced break-before/after applies and this is a genuinely fresh entry
                                 // (no resume state of any kind) - defer this box (and everything after it
                                 // in its parent's child loop) to a later pass entirely, rather than
                                 // positioning it now.
                                 RequestedBreakBeforeSlot = breakSlot;
-                                RequestedBreakBeforeTop = breakTop;
+                                RequestedBreakBeforeTop = breakTopWithMargin;
                                 return;
                             }
 
@@ -911,7 +919,7 @@ protected virtual void PerformLayoutImp(RGraphics g)
                             // before real pass-based deferral existed. Not ideal (this content doesn't
                             // get a fresh fragmentainer pass the way top-level content does), but correct
                             // rather than silently measured-but-never-positioned.
-                            top = breakTop;
+                            top = breakTopWithMargin;
                         }
                         else
                         {

Source/Test/HtmlRenderer.IntegrationTest/Fragmentation/PageBreakIntegrationTests.cs

@@ -28,13 +28,11 @@ namespace TheArtOfDev.HtmlRenderer.IntegrationTest.Fragmentation;
 /// only ever tests <c>BreakValues.IsForcedBreak</c> on <c>break-before</c>/<c>break-after</c>. Named-page
 /// attribution/transitions are out of scope per the port plan's general exclusion list.
 /// <para>
-/// Confirmed by actually running these against the real engine (not just reading source): three more real
+/// Confirmed by actually running these against the real engine (not just reading source): two more real
 /// behavioral differences from PeachPDF surfaced, each documented on its own test below -
 /// <c>BreakBeforeAlways_IsAcceptedAsAForcedBreak_UnlikePeachPDF</c> (inverted, not dropped: a deliberate,
-/// documented design choice - see <c>BreakValues.IsForcedBreak</c>'s own remark),
-/// <c>ForcedBreak_MarginAfterBreak_IsPreservedNotTruncated</c> (Ignored: <c>TryGetForcedBreakTarget</c>'s
-/// <c>targetTop</c> is always the raw <c>PageTopOf(slot)</c>, discarding the box's own margin entirely
-/// rather than adding it back), and the "container left behind" gap extending to margin-truncation-caused
+/// documented design choice - see <c>BreakValues.IsForcedBreak</c>'s own remark), and the "container left
+/// behind" gap extending to margin-truncation-caused
 /// overflow specifically (2 tests Ignored - <c>EnforceKeepWithNext</c>'s pull only fires on an actual slot
 /// gap between a container and ITS OWN previous sibling, which a grandchild's margin truncation alone never
 /// creates, unlike <c>RelocateIfNeeded</c>'s straddle-triggered relocation - the case
@@ -283,12 +281,6 @@ public async Task HugeMultiPageMargin_TruncatesToZero_LandsOnVeryNextPage()
     // A forced break already relocates the previous sibling's bottom to the next page's top - per
     // css-break-3 §5.2, PeachPDF preserves (does not truncate) the margin AFTER a forced break.
     [TestMethod]
-    [Ignore("Confirmed gap: BlockFragmentation.TryGetForcedBreakTarget's targetTop is always the raw "
-        + "container.PageTopOf(slot) - the box's own MarginTopCollapse is used only to decide WHICH slot "
-        + "the natural position falls in, never added back into the final target. So a forced-break box's "
-        + "own margin-top is silently discarded, not preserved, unlike PeachPDF. Confirmed by running this "
-        + "test unignored: the box lands at exactly PageTopOf(1) (320 in this fixture's original 300/20 "
-        + "page grid) rather than PageTopOf(1)+50.")]
     public async Task ForcedBreak_MarginAfterBreak_IsPreservedNotTruncated()
     {
         var (root, container) = await BuildAsync(

Source/Test/HtmlRenderer.Test/Fragmentation/ForcedBreakTargetIsTheFramesTests.cs

@@ -143,14 +143,6 @@ public void ConsecutiveForcedBreaks_StepPastTheMarkerRatherThanCollapsingOntoIt(
     // §5.2 preserves the margin on the new page's side of a FORCED break, so the box lands one margin
     // below the target rather than on it - which is exactly why the target is worth asserting
     // separately from the position.
-    [Ignore("This port does not preserve a box's own top margin at a forced-break target - confirmed by " +
-            "direct source read and empirically. BlockFragmentation.TryGetForcedBreakTarget returns the raw " +
-            "slot boundary (Core/Fragmentation/BlockFragmentation.cs ~87: 'targetTop = " +
-            "container.PageTopOf(slot)'), and every consumer places the box flush there with no margin " +
-            "added: CssBox.cs ~914 ('top = breakTop') for the immediate-placement path, and ~974 " +
-            "(ResumeTopOverride: childBox.RequestedBreakBeforeTop) for the deferred-pass path that resumes " +
-            "via ~894 ('top = _resumeTopOverride.Value'). A 30px break-before box lands at SlotTop(1) " +
-            "exactly, not SlotTop(1)+30, unlike PeachPDF's css-break-3 §5.2 margin preservation.")]
     [TestMethod]
     public void TargetIsTheBoundary_AndThePreservedMarginIsAddedToIt()
     {