Fixed the pager to strip OSC sequences before ANSI parsing, preserving visible hyperlink text, colors, and width calculations

When ppaged() receives Rich output containing hyperlinks, Rich emits OSC 8 sequences that prompt-toolkit's ANSI parser does not understand. Their contents become visible pager text: a linked click here renders as 8;id=...;https://example.comclick here8;;. This also corrupts width calculations and searchable text.

This change strips unsupported OSC sequences before passing captured output to cmd2's new internal pager.

Author: tleonhardt

cmd2/pager.py

@@ -1,5 +1,6 @@
 """A pager view hosted by the main prompt-toolkit application."""
 
+import re
 import threading
 from collections.abc import Callable
 from functools import partial
@@ -20,9 +21,14 @@
 from prompt_toolkit.utils import get_cwidth
 from prompt_toolkit.widgets import SearchToolbar, TextArea
 
+_OSC_RE = re.compile(r"\x1b\][^\x07\x1b]*(?:\x07|\x1b\\)")
+
 
 def _fragments(text: str) -> StyleAndTextTuples:
     """Parse captured output, dropping the trailing newline that ends its last line."""
+    # prompt-toolkit's ANSI parser does not handle OSC sequences, including Rich
+    # hyperlinks. Remove their metadata while retaining visible text and SGR styles.
+    text = _OSC_RE.sub("", text)
     return to_formatted_text(ANSI(text.removesuffix("\n")))
 
 

tests/test_command_toolbar.py

@@ -17,6 +17,7 @@
 from prompt_toolkit.layout import HSplit, Layout, Window
 from prompt_toolkit.output import DummyOutput
 from prompt_toolkit.shortcuts import PromptSession
+from rich.console import Console
 
 from cmd2 import Cmd, command_toolbar
 from cmd2.pager import Pager, output_fits
@@ -808,6 +809,24 @@ def test_pager_styles_and_wrapping(chop) -> None:
     assert "ansired" in lexer(0)[0][0]
 
 
+@pytest.mark.parametrize("chop", [False, True])
+@pytest.mark.parametrize("terminator", ["\x1b\\", "\x07"], ids=["ST", "BEL"])
+def test_pager_rich_hyperlinks(chop, terminator) -> None:
+    console = Console(force_terminal=True, color_system="standard", no_color=False)
+    with console.capture() as capture:
+        console.print("[link=https://example.com][red]click here[/red][/link] after")
+    captured = capture.get()
+    assert "\x1b]8;" in captured
+    captured = captured.replace("\x1b\\", terminator)
+
+    pager = Pager(captured, chop=chop)
+    assert pager.text.text == "click here after"
+    lexer = pager.text.lexer.lex_document(pager.text.document)
+    assert "ansired" in lexer(0)[0][0]
+    assert output_fits(captured, len("click here after"), 1, chop=chop)
+    assert not output_fits(captured, len("click here after") - 1, 1, chop=chop)
+
+
 @pytest.mark.parametrize("chop", [False, True])
 def test_output_fits_measures_styled_and_wide_text(chop) -> None:
     # Forty double-width characters occupy eighty columns, and styling them adds