gh-131507: Clean up tests and type checking for _pyrepl (#131509)

Author: ambv

Diff for: Lib/_colorize.py

@@ -1,23 +1,64 @@
+from __future__ import annotations
 import io
 import os
 import sys
 
 COLORIZE = True
 
+# types
+if False:
+    from typing import IO
+
 
 class ANSIColors:
-    BACKGROUND_YELLOW = "\x1b[43m"
-    BOLD_GREEN = "\x1b[1;32m"
-    BOLD_MAGENTA = "\x1b[1;35m"
-    BOLD_RED = "\x1b[1;31m"
+    RESET = "\x1b[0m"
+
     BLACK = "\x1b[30m"
+    BLUE = "\x1b[34m"
+    CYAN = "\x1b[36m"
     GREEN = "\x1b[32m"
-    GREY = "\x1b[90m"
     MAGENTA = "\x1b[35m"
     RED = "\x1b[31m"
-    RESET = "\x1b[0m"
+    WHITE = "\x1b[37m"  # more like LIGHT GRAY
     YELLOW = "\x1b[33m"
 
+    BOLD_BLACK = "\x1b[1;30m"  # DARK GRAY
+    BOLD_BLUE = "\x1b[1;34m"
+    BOLD_CYAN = "\x1b[1;36m"
+    BOLD_GREEN = "\x1b[1;32m"
+    BOLD_MAGENTA = "\x1b[1;35m"
+    BOLD_RED = "\x1b[1;31m"
+    BOLD_WHITE = "\x1b[1;37m"  # actual WHITE
+    BOLD_YELLOW = "\x1b[1;33m"
+
+    # intense = like bold but without being bold
+    INTENSE_BLACK = "\x1b[90m"
+    INTENSE_BLUE = "\x1b[94m"
+    INTENSE_CYAN = "\x1b[96m"
+    INTENSE_GREEN = "\x1b[92m"
+    INTENSE_MAGENTA = "\x1b[95m"
+    INTENSE_RED = "\x1b[91m"
+    INTENSE_WHITE = "\x1b[97m"
+    INTENSE_YELLOW = "\x1b[93m"
+
+    BACKGROUND_BLACK = "\x1b[40m"
+    BACKGROUND_BLUE = "\x1b[44m"
+    BACKGROUND_CYAN = "\x1b[46m"
+    BACKGROUND_GREEN = "\x1b[42m"
+    BACKGROUND_MAGENTA = "\x1b[45m"
+    BACKGROUND_RED = "\x1b[41m"
+    BACKGROUND_WHITE = "\x1b[47m"
+    BACKGROUND_YELLOW = "\x1b[43m"
+
+    INTENSE_BACKGROUND_BLACK = "\x1b[100m"
+    INTENSE_BACKGROUND_BLUE = "\x1b[104m"
+    INTENSE_BACKGROUND_CYAN = "\x1b[106m"
+    INTENSE_BACKGROUND_GREEN = "\x1b[102m"
+    INTENSE_BACKGROUND_MAGENTA = "\x1b[105m"
+    INTENSE_BACKGROUND_RED = "\x1b[101m"
+    INTENSE_BACKGROUND_WHITE = "\x1b[107m"
+    INTENSE_BACKGROUND_YELLOW = "\x1b[103m"
+
 
 NoColors = ANSIColors()
 
@@ -26,14 +67,16 @@ class ANSIColors:
         setattr(NoColors, attr, "")
 
 
-def get_colors(colorize: bool = False, *, file=None) -> ANSIColors:
+def get_colors(
+    colorize: bool = False, *, file: IO[str] | IO[bytes] | None = None
+) -> ANSIColors:
     if colorize or can_colorize(file=file):
         return ANSIColors()
     else:
         return NoColors
 
 
-def can_colorize(*, file=None) -> bool:
+def can_colorize(*, file: IO[str] | IO[bytes] | None = None) -> bool:
     if file is None:
         file = sys.stdout
 
@@ -66,4 +109,4 @@ def can_colorize(*, file=None) -> bool:
     try:
         return os.isatty(file.fileno())
     except io.UnsupportedOperation:
-        return file.isatty()
+        return hasattr(file, "isatty") and file.isatty()

Diff for: Lib/_pyrepl/commands.py

@@ -456,7 +456,7 @@ def do(self) -> None:
 class show_history(Command):
     def do(self) -> None:
         from .pager import get_pager
-        from site import gethistoryfile  # type: ignore[attr-defined]
+        from site import gethistoryfile
 
         history = os.linesep.join(self.reader.history[:])
         self.reader.console.restore()

Diff for: Lib/_pyrepl/console.py

@@ -19,7 +19,7 @@
 
 from __future__ import annotations
 
-import _colorize  # type: ignore[import-not-found]
+import _colorize
 
 from abc import ABC, abstractmethod
 import ast
@@ -162,7 +162,7 @@ def __init__(
         *,
         local_exit: bool = False,
     ) -> None:
-        super().__init__(locals=locals, filename=filename, local_exit=local_exit)  # type: ignore[call-arg]
+        super().__init__(locals=locals, filename=filename, local_exit=local_exit)
         self.can_colorize = _colorize.can_colorize()
 
     def showsyntaxerror(self, filename=None, **kwargs):

Diff for: Lib/_pyrepl/mypy.ini

@@ -4,8 +4,9 @@
 
 [mypy]
 files = Lib/_pyrepl
+mypy_path = $MYPY_CONFIG_FILE_DIR/../../Misc/mypy
 explicit_package_bases = True
-python_version = 3.12
+python_version = 3.13
 platform = linux
 pretty = True
 
@@ -22,3 +23,7 @@ check_untyped_defs = False
 # Various internal modules that typeshed deliberately doesn't have stubs for:
 [mypy-_abc.*,_opcode.*,_overlapped.*,_testcapi.*,_testinternalcapi.*,test.*]
 ignore_missing_imports = True
+
+# Other untyped parts of the stdlib
+[mypy-idlelib.*]
+ignore_missing_imports = True

Diff for: Lib/_pyrepl/reader.py

@@ -26,11 +26,11 @@
 from contextlib import contextmanager
 from dataclasses import dataclass, field, fields
 import unicodedata
-from _colorize import can_colorize, ANSIColors  # type: ignore[import-not-found]
+from _colorize import can_colorize, ANSIColors
 
 
 from . import commands, console, input
-from .utils import ANSI_ESCAPE_SEQUENCE, wlen, str_width
+from .utils import wlen, unbracket, str_width
 from .trace import trace
 
 
@@ -421,42 +421,15 @@ def calc_screen(self) -> list[str]:
 
     @staticmethod
     def process_prompt(prompt: str) -> tuple[str, int]:
-        """Process the prompt.
+        r"""Return a tuple with the prompt string and its visible length.
 
-        This means calculate the length of the prompt. The character \x01
-        and \x02 are used to bracket ANSI control sequences and need to be
-        excluded from the length calculation.  So also a copy of the prompt
-        is returned with these control characters removed."""
-
-        # The logic below also ignores the length of common escape
-        # sequences if they were not explicitly within \x01...\x02.
-        # They are CSI (or ANSI) sequences  ( ESC [ ... LETTER )
-
-        # wlen from utils already excludes ANSI_ESCAPE_SEQUENCE chars,
-        # which breaks the logic below so we redefine it here.
-        def wlen(s: str) -> int:
-            return sum(str_width(i) for i in s)
-
-        out_prompt = ""
-        l = wlen(prompt)
-        pos = 0
-        while True:
-            s = prompt.find("\x01", pos)
-            if s == -1:
-                break
-            e = prompt.find("\x02", s)
-            if e == -1:
-                break
-            # Found start and end brackets, subtract from string length
-            l = l - (e - s + 1)
-            keep = prompt[pos:s]
-            l -= sum(map(wlen, ANSI_ESCAPE_SEQUENCE.findall(keep)))
-            out_prompt += keep + prompt[s + 1 : e]
-            pos = e + 1
-        keep = prompt[pos:]
-        l -= sum(map(wlen, ANSI_ESCAPE_SEQUENCE.findall(keep)))
-        out_prompt += keep
-        return out_prompt, l
+        The prompt string has the zero-width brackets recognized by shells
+        (\x01 and \x02) removed.  The length ignores anything between those
+        brackets as well as any ANSI escape sequences.
+        """
+        out_prompt = unbracket(prompt, including_content=False)
+        visible_prompt = unbracket(prompt, including_content=True)
+        return out_prompt, wlen(visible_prompt)
 
     def bow(self, p: int | None = None) -> int:
         """Return the 0-based index of the word break preceding p most

Diff for: Lib/_pyrepl/readline.py

@@ -32,7 +32,7 @@
 from dataclasses import dataclass, field
 
 import os
-from site import gethistoryfile   # type: ignore[attr-defined]
+from site import gethistoryfile
 import sys
 from rlcompleter import Completer as RLCompleter
 

Diff for: Lib/_pyrepl/utils.py

@@ -3,23 +3,36 @@
 import functools
 
 ANSI_ESCAPE_SEQUENCE = re.compile(r"\x1b\[[ -@]*[A-~]")
+ZERO_WIDTH_BRACKET = re.compile(r"\x01.*?\x02")
+ZERO_WIDTH_TRANS = str.maketrans({"\x01": "", "\x02": ""})
 
 
 @functools.cache
 def str_width(c: str) -> int:
     if ord(c) < 128:
         return 1
     w = unicodedata.east_asian_width(c)
-    if w in ('N', 'Na', 'H', 'A'):
+    if w in ("N", "Na", "H", "A"):
         return 1
     return 2
 
 
 def wlen(s: str) -> int:
-    if len(s) == 1 and s != '\x1a':
+    if len(s) == 1 and s != "\x1a":
         return str_width(s)
     length = sum(str_width(i) for i in s)
     # remove lengths of any escape sequences
     sequence = ANSI_ESCAPE_SEQUENCE.findall(s)
-    ctrl_z_cnt = s.count('\x1a')
+    ctrl_z_cnt = s.count("\x1a")
     return length - sum(len(i) for i in sequence) + ctrl_z_cnt
+
+
+def unbracket(s: str, including_content: bool = False) -> str:
+    r"""Return `s` with \001 and \002 characters removed.
+
+    If `including_content` is True, content between \001 and \002 is also
+    stripped.
+    """
+    if including_content:
+        return ZERO_WIDTH_BRACKET.sub("", s)
+    return s.translate(ZERO_WIDTH_TRANS)

Diff for: Lib/test/test_pyrepl/support.py

@@ -6,14 +6,24 @@
 from _pyrepl.console import Console, Event
 from _pyrepl.readline import ReadlineAlikeReader, ReadlineConfig
 from _pyrepl.simple_interact import _strip_final_indent
+from _pyrepl.utils import unbracket, ANSI_ESCAPE_SEQUENCE
+
+
+class ScreenEqualMixin:
+    def assert_screen_equal(
+        self, reader: ReadlineAlikeReader, expected: str, clean: bool = False
+    ):
+        actual = clean_screen(reader) if clean else reader.screen
+        expected = expected.split("\n")
+        self.assertListEqual(actual, expected)
 
 
 def multiline_input(reader: ReadlineAlikeReader, namespace: dict | None = None):
     saved = reader.more_lines
     try:
         reader.more_lines = partial(more_lines, namespace=namespace)
-        reader.ps1 = reader.ps2 = ">>>"
-        reader.ps3 = reader.ps4 = "..."
+        reader.ps1 = reader.ps2 = ">>> "
+        reader.ps3 = reader.ps4 = "... "
         return reader.readline()
     finally:
         reader.more_lines = saved
@@ -38,18 +48,22 @@ def code_to_events(code: str):
         yield Event(evt="key", data=c, raw=bytearray(c.encode("utf-8")))
 
 
-def clean_screen(screen: Iterable[str]):
+def clean_screen(reader: ReadlineAlikeReader) -> list[str]:
     """Cleans color and console characters out of a screen output.
 
     This is useful for screen testing, it increases the test readability since
     it strips out all the unreadable side of the screen.
     """
     output = []
-    for line in screen:
-        if line.startswith(">>>") or line.startswith("..."):
-            line = line[3:]
+    for line in reader.screen:
+        line = unbracket(line, including_content=True)
+        line = ANSI_ESCAPE_SEQUENCE.sub("", line)
+        for prefix in (reader.ps1, reader.ps2, reader.ps3, reader.ps4):
+            if line.startswith(prefix):
+                line = line[len(prefix):]
+                break
         output.append(line)
-    return "\n".join(output).strip()
+    return output
 
 
 def prepare_reader(console: Console, **kwargs):
@@ -99,6 +113,9 @@ def handle_all_events(
     prepare_console=partial(prepare_console, width=10),
 )
 
+reader_no_colors = partial(prepare_reader, can_colorize=False)
+reader_force_colors = partial(prepare_reader, can_colorize=True)
+
 
 class FakeConsole(Console):
     def __init__(self, events, encoding="utf-8") -> None: