Merge pull request #2799 from jayaddison/issue-2688/nf-escaping

ANSI: nF-escape symbol "(" decoding issue

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Use `Console(stderr=True)` in `rich.traceback.install` to support io redirection.
 - Fixes superfluous spaces in html output https://github.com/Textualize/rich/issues/2832
 - Fixed duplicate output in Jupyter https://github.com/Textualize/rich/pulls/2804
+- Filter ANSI character-encoding-change codes in `Text.from_ansi` parser
 - Fixes traceback failing when a frame filename is unreadable https://github.com/Textualize/rich/issues/2821
 
 ### Added

CONTRIBUTORS.md

@@ -64,3 +64,4 @@ The following people have contributed to the development of Rich:
 - [Zhe Huang](https://github.com/onlyacat)
 - [Ke Sun](https://github.com/ksun212)
 - [Qiming Xu](https://github.com/xqm32)
+- [James Addison](https://github.com/jayaddison)

rich/ansi.py

@@ -43,6 +43,9 @@ def _ansi_tokenize(ansi_text: str) -> Iterable[_AnsiToken]:
         if start > position:
             yield _AnsiToken(ansi_text[position:start])
         if sgr:
+            if sgr == "(":
+                position = end + 1
+                continue
             if sgr.endswith("m"):
                 yield _AnsiToken("", sgr[1:-1], osc)
         else:

tests/test_ansi.py

@@ -1,3 +1,5 @@
+import pytest
+
 from rich.ansi import AnsiDecoder
 from rich.console import Console
 from rich.style import Style
@@ -45,3 +47,24 @@ def test_decode_example():
     print(repr(result))
     expected = "\x1b[1mC:\\Users\\stefa\\AppData\\Local\\Temp\\tmp3ydingba:\x1b[0m In function '\x1b[1mmain\x1b[0m':\n\x1b[1mC:\\Users\\stefa\\AppData\\Local\\Temp\\tmp3ydingba:3:5:\x1b[0m \x1b[1;35mwarning: \x1b[0munused variable '\x1b[1ma\x1b[0m' \n[\x1b[1;35m-Wunused-variable\x1b[0m]\n    3 | int \x1b[1;35ma\x1b[0m=1;\n      |     \x1b[1;35m^\x1b[0m\n"
     assert result == expected
+
+
+@pytest.mark.parametrize(
+    "ansi_bytes, expected_text",
+    [
+        # https://github.com/Textualize/rich/issues/2688
+        (
+            b"\x1b[31mFound 4 errors in 2 files (checked 18 source files)\x1b(B\x1b[m\n",
+            "Found 4 errors in 2 files (checked 18 source files)",
+        ),
+        # https://mail.python.org/pipermail/python-list/2007-December/424756.html
+        (b"Hallo", "Hallo"),
+        (b"\x1b(BHallo", "Hallo"),
+        (b"\x1b(JHallo", "Hallo"),
+        (b"\x1b(BHal\x1b(Jlo", "Hallo"),
+    ],
+)
+def test_decode_issue_2688(ansi_bytes, expected_text):
+    text = Text.from_ansi(ansi_bytes.decode())
+
+    assert str(text) == expected_text