raw derive PDF: Durchstreichung und Textmarker lassen Programmtext aus, wie Vertrag und Body von #231 sagen; am Korpus unverändert (#231); 10.1.0-beta.6

Files changed:
- CHANGES.md
- VERSION
- tools/chemenu/filters/pdf_layout.py
- tools/chemenu/tests/test_raw_derive_binary.py

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SnAJ7Z3CpVD3PRbN73QtU2

CHANGES.md

@@ -14,7 +14,7 @@ place only: `instructions/dev/version-parts.md` § The candidate model.
 
 ---
 
-## 10.1.0-beta.5 - 2026-10-14 - raw derive PDF: Auszeichnungen auf ein Minimum - Struktur zuerst, ~~ ** * nur wo eindeutig, Bildseiten-CHECK nur für Inhaltsbilder
+## 10.1.0-beta.6 - 2026-10-14 - raw derive PDF: Durchstreichung und Textmarker lassen Programmtext aus, wie der Vertrag sagt (#231)
 
 **Author:** Torben Nehmer
 
@@ -27,6 +27,7 @@ place only: `instructions/dev/version-parts.md` § The candidate model.
 **Low impact**
 - instructions/dev: Konverter-Vergleich – eigene Ableitung gegen Referenzwerkzeuge am privaten Korpus, mit Grundlinie
 - instructions/dev: converter-comparison nennt harness/compare/README.md als Ort der Einrichtung
+- raw derive PDF: Durchstreichung und Textmarker lassen Programmtext aus, wie der Vertrag sagt (#231)
 <!-- /wikitool:bumps -->
 
 ### Konverter-Tests gegen echte Dokumente im privaten Repository

VERSION

@@ -1 +1 @@
-10.1.0-beta.5
+10.1.0-beta.6

tools/chemenu/filters/pdf_layout.py

@@ -491,7 +491,7 @@ def context(layouts: list[PageLayout]) -> Context:
     return Context(body_size, body_colour, templates(layouts))
 
 
-def _struck(layout: PageLayout, grid: Grid, template: Templates, table: set[int]) -> set[int]:
+def _struck(layout: PageLayout, grid: Grid, template: Templates, left_alone: set[int]) -> set[int]:
     """Rule 2: a thin line through the middle of at least STRIKE_MIN_CHARS characters that does
     not reach further than STRIKE_OVERHANG past them, measured in the characters' own frame
     (so text turned by a quarter is struck by a vertical line). Not a table's ruling, not a
@@ -505,7 +505,7 @@ def _struck(layout: PageLayout, grid: Grid, template: Templates, table: set[int]
         along = [
             (_centre(layout.chars[i].box)[0 if horizontal else 1], i)
             for i in range(len(layout.chars))
-            if layout.chars[i].direction in ((0, 180) if horizontal else (90, 270)) and i not in table
+            if layout.chars[i].direction in ((0, 180) if horizontal else (90, 270)) and i not in left_alone
         ]
         along.sort()
         keys = [key for key, _ in along]
@@ -536,7 +536,7 @@ def _struck(layout: PageLayout, grid: Grid, template: Templates, table: set[int]
     return found
 
 
-def _highlighted(layout: PageLayout, template: Templates, table: set[int]) -> dict[int, str]:
+def _highlighted(layout: PageLayout, template: Templates, left_alone: set[int]) -> dict[int, str]:
     """Rule 3: a bright, saturated fill drawn under the text, about as high as a line and no
     wider than the text it covers plus HIGHLIGHT_MAX_EXTRA type heights. The colour per character."""
     found: dict[int, str] = {}
@@ -552,7 +552,7 @@ def _highlighted(layout: PageLayout, template: Templates, table: set[int]) -> di
             continue
         covered = [
             i for i, char in enumerate(layout.chars)
-            if char.order > fill.order and i not in table and _inside(fill.box, *_centre(char.box))
+            if char.order > fill.order and i not in left_alone and _inside(fill.box, *_centre(char.box))
         ]
         if not covered:
             continue
@@ -604,9 +604,9 @@ def page_glyphs(layout: PageLayout, ctx: Context) -> list[Glyph]:
                         strong[i] = "bold"
                     if _is_italic(char):
                         italic.add(i)
-    for i, colour in _highlighted(layout, ctx.template, table).items():
+    for i, colour in _highlighted(layout, ctx.template, table | code).items():
         strong[i] = colour
-    struck = _struck(layout, grid, ctx.template, table)
+    struck = _struck(layout, grid, ctx.template, table | code)
     return [
         Glyph(char.text, strong[i] is not None, i in struck, i in italic, strong[i] if strong[i] not in (None, "bold") else None)
         for i, char in enumerate(layout.chars)

tools/chemenu/tests/test_raw_derive_binary.py

@@ -299,12 +299,12 @@ def test_text_turned_by_a_quarter_is_struck_by_a_line_in_its_own_direction_only(
 def test_program_text_is_left_alone(tree):
     code = [
         [("if", {"bold": True, "color": BLUE}), " (x == 1) {"],
-        ["    ", ("return", {"bold": True, "color": BLUE}), " f(a, b);"],
+        ["    ", ("return", {"bold": True, "color": BLUE, "highlight": (1, 1, 0)}), " f(a, b);"],
-        ["  y = g(x) + h[0];"],
+        ["  ", ("y = g(x)", {"strike": True}), " + h[0];"],
         ["}"],
     ]
-    _header, text = _derive_pdf(tree, build_styled_pdf([StyledPage(code)]))
+    header, text = _derive_pdf(tree, build_styled_pdf([StyledPage(code)]))
-    assert "*" not in text
+    assert "*" not in text and "~" not in text and "markings" not in header
 
 
 @needs_pypdf